35 results
(View BibTeX file of all listed publications)
2024
Stable Video Portraits
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, European Conference on Computer Vision (ECCV 2024), October 2024 (inproceedings) Accepted
Rapid advances in the field of generative AI and text-to-image methods in particular have transformed the way we interact with and perceive computer-generated imagery today. In parallel, much progress has been made in 3D face reconstruction, using 3D Morphable Models (3DMM). In this paper, we present Stable Video Portraits, a novel hybrid 2D/3D generation method that outputs photorealistic videos of talking faces leveraging a large pre-trained text-to-image prior (2D), controlled via a 3DMM (3D). Specifically, we introduce a person-specific fine-tuning of a general 2D stable diffusion model which we lift to a video model by providing temporal 3DMM sequences as conditioning and by introducing a temporal denoising procedure. As an output, this model generates temporally smooth imagery of a person with 3DMM-based controls, i.e., a person-specific avatar. The facial appearance of this person-specific avatar can be edited and morphed to text-defined celebrities, without any test-time fine-tuning. The method is analyzed quantitatively and qualitatively, and we show that our method outperforms state-of-the-art monocular head avatar methods.
Synthesizing Environment-Specific People in Photographs
Ostrek, M., O’Sullivan, C., Black, M., Thies, J.
In European Conference on Computer Vision (ECCV 2024), LNCS, Springer Cham, European Conference on Computer Vision (ECCV 2024), October 2024 (inproceedings) Accepted
We present ESP, a novel method for context-aware full-body generation, that enables photo-realistic synthesis and inpainting of people wearing clothing that is semantically appropriate for the scene depicted in an input photograph. ESP is conditioned on a 2D pose and contextual cues that are extracted from the photograph of the scene and integrated into the generation process, where the clothing is modeled explicitly with human parsing masks (HPM). Generated HPMs are used as tight guiding masks for inpainting, such that no changes are made to the original background. Our models are trained on a dataset containing a set of in-the-wild photographs of people covering a wide range of different environments. The method is analyzed quantitatively and qualitatively, and we show that ESP outperforms the state-of-the-art on the task of contextual full-body generation.
Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles
Sklyarova, V., Zakharov, E., Hilliges, O., Black, M. J., Thies, J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), CVPR 2024, June 2024 (inproceedings)
We present HAAR, a new strand-based generative model for 3D human hairstyles. Specifically, based on textual inputs, HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines. Current AI-based generative models take advantage of powerful 2D priors to reconstruct 3D content in the form of point clouds, meshes, or volumetric functions. However, by using the 2D priors, they are intrinsically limited to only recovering the visual parts. Highly occluded hair structures can not be reconstructed with those methods, and they only model the "outer shell", which is not ready to be used in physics-based rendering or simulation pipelines. In contrast, we propose a first text-guided generative method that uses 3D hair strands as an underlying representation. Leveraging 2D visual question-answering (VQA) systems, we automatically annotate synthetic hair models that are generated from a small set of artist-created hairstyles. This allows us to train a latent diffusion model that operates in a common hairstyle UV space. In qualitative and quantitative studies, we demonstrate the capabilities of the proposed model and compare it to existing hairstyle generation approaches.
Neuropostors: Neural Geometry-aware 3D Crowd Character Impostors
Ostrek, M., Mitra, N. J., O’Sullivan, C.
In 2024 27th International Conference on Pattern Recognition (ICPR), Springer, 2024 27th International Conference on Pattern Recognition (ICPR), June 2024 (inproceedings) Accepted
Crowd rendering and animation was a very active research area over a decade ago, but in recent years this has lessened, mainly due to improvements in graphics acceleration hardware. Nevertheless, there is still a high demand for generating varied crowd appearances and animation for games, movie production, and mixed-reality applications. Current approaches are still limited in terms of both the behavioral and appearance aspects of virtual characters due to (i) high memory and computational demands; and (ii) person-hours needed of skilled artists in the context of short production cycles. A promising previous approach to generating varied crowds was the use of pre-computed impostor representations for crowd characters, which could replace an animation of a 3D mesh with a simplified 2D impostor for every frame of an animation sequence, e.g., Geopostors [1]. However, with their high memory demands at a time when improvements in consumer graphics accelerators were outpacing memory availability, the practicality of such methods was limited. Inspired by this early work and recent advances in the field of Neural Rendering, we present a new character representation: Neuropostors. We train a Convolutional Neural Network as a means of compressing both the geometric properties and animation key-frames for a 3D character, thereby allowing for constant-time rendering of animated characters from arbitrary camera views. Our method also allows for explicit illumination and material control, by utilizing a flexible rendering equation that is connected to the outputs of the neural network.
TECA: Text-Guided Generation and Editing of Compositional 3D Avatars
Zhang, H., Feng, Y., Kulits, P., Wen, Y., Thies, J., Black, M. J.
In International Conference on 3D Vision (3DV 2024), 3DV 2024, March 2024 (inproceedings) To be published
Our goal is to create a realistic 3D facial avatar with hair and accessories using only a text description. While this challenge has attracted significant recent interest, existing methods either lack realism, produce unrealistic shapes, or do not support editing, such as modifications to the hairstyle. We argue that existing methods are limited because they employ a monolithic modeling approach, using a single representation for the head, face, hair, and accessories. Our observation is that the hair and face, for example, have very different structural qualities that benefit from different representations. Building on this insight, we generate avatars with a compositional model, in which the head, face, and upper body are represented with traditional 3D meshes, and the hair, clothing, and accessories with neural radiance fields (NeRF). The model-based mesh representation provides a strong geometric prior for the face region, improving realism while enabling editing of the person's appearance. By using NeRFs to represent the remaining components, our method is able to model and synthesize parts with complex geometry and appearance, such as curly hair and fluffy scarves. Our novel system synthesizes these high-quality compositional avatars from text descriptions. The experimental results demonstrate that our method, Text-guided generation and Editing of Compositional Avatars (TECA), produces avatars that are more realistic than those of recent methods while being editable because of their compositional nature. For example, our TECA enables the seamless transfer of compositional features like hairstyles, scarves, and other accessories between avatars. This capability supports applications such as virtual try-on.
GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar
Kabadayi, B., Zielonka, W., Bhatnagar, B. L., Pons-Moll, G., Thies, J.
In International Conference on 3D Vision (3DV), March 2024 (inproceedings)
Digital humans and, especially, 3D facial avatars have raised a lot of attention in the past years, as they are the backbone of several applications like immersive telepresence in AR or VR. Despite the progress, facial avatars reconstructed from commodity hardware are incomplete and miss out on parts of the side and back of the head, severely limiting the usability of the avatar. This limitation in prior work stems from their requirement of face tracking, which fails for profile and back views. To address this issue, we propose to learn person-specific animatable avatars from images without assuming to have access to precise facial expression tracking. At the core of our method, we leverage a 3D-aware generative model that is trained to reproduce the distribution of facial expressions from the training data. To train this appearance model, we only assume to have a collection of 2D images with the corresponding camera parameters. For controlling the model, we learn a mapping from 3DMM facial expression parameters to the latent space of the generative model. This mapping can be learned by sampling the latent space of the appearance model and reconstructing the facial parameters from a normalized frontal view, where facial expression estimation performs well. With this scheme, we decouple 3D appearance reconstruction and animation control to achieve high fidelity in image synthesis. In a series of experiments, we compare our proposed technique to state-of-the-art monocular methods and show superior quality while not requiring expression tracking of the training data.
2023
Instant Volumetric Head Avatars
Zielonka, W., Bolkart, T., Thies, J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), CVPR 2023, June 2023 (inproceedings)
We present Instant Volumetric Head Avatars (INSTA),a novel approach for reconstructing photo-realistic digital avatars instantaneously. INSTA models a dynamic neural radiance field based on neural graphics primitives embedded around a parametric face model. Our pipeline is trained on a single monocular RGB portrait video that observes the subject under different expressions and views. While state-of-the-art methods take up to several days to train an avatar, our method can reconstruct a digital avatar in less than 10 minutes on modern GPU hardware, which is orders of magnitude faster than previous solutions. In addition, it allows for the interactive rendering of novel poses and expressions. By leveraging the geometry prior of the underlying parametric face model, we demonstrate that INSTA extrapolates to unseen poses. In quantitative and qualitative studies on various subjects, INSTA outperforms state-of-the-art methods regarding rendering quality and training time.
MIME: Human-Aware 3D Scene Generation
Yi, H., Huang, C. P., Tripathi, S., Hering, L., Thies, J., Black, M. J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 12965-12976, CVPR 2023, June 2023 (inproceedings) Accepted
Generating realistic 3D worlds occupied by moving humans has many applications in games, architecture, and synthetic data creation. But generating such scenes is expensive and labor intensive. Recent work generates human poses and motions given a 3D scene. Here, we take the opposite approach and generate 3D indoor scenes given 3D human motion. Such motions can come from archival motion capture or from IMU sensors worn on the body, effectively turning human movement in a “scanner” of the 3D world. Intuitively, human movement indicates the free-space in a room and human contact indicates surfaces or objects that support activities such as sitting, lying or touching. We propose MIME (Mining Interaction and Movement to infer 3D Environments), which is a generative model of indoor scenes that produces furniture layouts that are consistent with the human movement. MIME uses an auto-regressive transformer architecture that takes the already generated objects in the scene as well as the human motion as input, and outputs the next plausible object. To train MIME, we build a dataset by populating the 3D FRONT scene dataset with 3D humans. Our experiments show that MIME produces more diverse and plausible 3D scenes than a recent generative scene method that does not know about human movement. Code and data will be available for research at https://mime.is.tue.mpg.de.
DINER: Depth-aware Image-based Neural Radiance Fields
Prinzler, M., Hilliges, O., Thies, J.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), CVPR 2023, 2023 (inproceedings) Accepted
We present Depth-aware Image-based NEural Radiance fields (DINER). Given a sparse set of RGB input views, we predict depth and feature maps to guide the reconstruction of a volumetric scene representation that allows us to render 3D objects under novel views. Specifically, we propose novel techniques to incorporate depth information into feature fusion and efficient scene sampling. In comparison to the previous state of the art, DINER achieves higher synthesis quality and can process input views with greater disparity. This allows us to capture scenes more completely without changing capturing hardware requirements and ultimately enables larger viewpoint changes during novel view synthesis. We evaluate our method by synthesizing novel views, both for human heads and for general objects, and observe significantly improved qualitative results and increased perceptual metrics compared to the previous state of the art. The code is publicly available for research purposes.
2022
Towards Metrical Reconstruction of Human Faces
Zielonka, W., Bolkart, T., Thies, J.
In Computer Vision – ECCV 2022, 13, pages: 250-269, Lecture Notes in Computer Science, 13673, (Editors: Avidan, Shai and Brostow, Gabriel and Cissé, Moustapha and Farinella, Giovanni Maria and Hassner, Tal), Springer, Cham, 17th European Conference on Computer Vision (ECCV 2022), October 2022 (inproceedings)
Face reconstruction and tracking is a building block of numerous applications in AR/VR, human-machine interaction, as well as medical applications. Most of these applications rely on a metrically correct prediction of the shape, especially, when the reconstructed subject is put into a metrical context (i.e., when there is a reference object of known size). A metrical reconstruction is also needed for any application that measures distances and dimensions of the subject (e.g., to virtually fit a glasses frame). State-of-the-art methods for face reconstruction from a single image are trained on large 2D image datasets in a self-supervised fashion. However, due to the nature of a perspective projection they are not able to reconstruct the actual face dimensions, and even predicting the average human face outperforms some of these methods in a metrical sense. To learn the actual shape of a face, we argue for a supervised training scheme. Since there exists no large-scale 3D dataset for this task, we annotated and unified small- and medium-scale databases. The resulting unified dataset is still a medium-scale dataset with more than 2k identities and training purely on it would lead to overfitting. To this end, we take advantage of a face recognition network pretrained on a large-scale 2D image dataset, which
provides distinct features for different faces and is robust to expression, illumination, and camera changes. Using these features, we train our face shape estimator in a supervised fashion, inheriting the robustness and generalization of the face recognition network. Our method, which we call MICA (MetrIC fAce), outperforms the state-of-the-art reconstruction methods by a large margin, both on current non-metric benchmarks as well as on our metric benchmarks (15% and 24% lower average error on NoW, respectively). Project website: https://zielon.github.io/mica/.
Human-Aware Object Placement for Visual Environment Reconstruction
Yi, H., Huang, C. P., Tzionas, D., Kocabas, M., Hassan, M., Tang, S., Thies, J., Black, M. J.
In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), pages: 3949-3960, IEEE, Piscataway, NJ, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), June 2022 (inproceedings)
Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them. In fact, we demonstrate that these human-scene interactions (HSIs) can be leveraged to improve the 3D reconstruction of a scene from a monocular RGB video. Our key idea is that, as a person moves through a scene and interacts with it, we accumulate HSIs across multiple input images, and optimize the 3D scene to reconstruct a consistent, physically plausible and functional 3D scene layout. Our optimization-based approach exploits three types of HSI constraints: (1) humans that move in a scene are occluded or occlude objects, thus, defining the depth ordering of the objects, (2) humans move through free space and do not interpenetrate objects, (3) when humans and objects are in contact, the contact surfaces occupy the same place in space. Using these constraints in an optimization formulation across all observations, we significantly improve the 3D scene layout reconstruction. Furthermore, we show that our scene reconstruction can be used to refine the initial 3D human pose and shape (HPS) estimation. We evaluate the 3D scene layout reconstruction and HPS estimation qualitatively and quantitatively using the PROX and PiGraphs datasets. The code and data are available for research purposes at https://mover.is.tue.mpg.de/.
Neural Head Avatars from Monocular RGB Videos
Grassal, P., Prinzler, M., Leistner, T., Rother, C., Nießner, M., Thies, J.
In 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) , pages: 18632-18643 , IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2022 (inproceedings)
We present Neural Head Avatars, a novel neural representation that explicitly models the surface geometry and appearance of an animatable human avatar that can be used for teleconferencing in AR/VR or other applications in the movie or games industry that rely on a digital human. Our representation can be learned from a monocular RGB portrait video that features a range of different expressions and views. Specifically, we propose a hybrid representation consisting of a morphable model for the coarse shape and expressions of the face, and two feed-forward networks, predicting vertex offsets of the underlying mesh as well as a view- and expression-dependent texture. We demonstrate that this representation is able to accurately extrapolate to unseen poses and view points, and generates natural expressions while providing sharp texture details. Compared to previous works on head avatars, our method provides a disentangled shape and appearance model of the complete human head (including hair) that is compatible with the standard graphics pipeline. Moreover, it quantitatively and qualitatively outperforms current state of the art in terms of reconstruction quality and novel-view synthesis.
2021
Dynamic Surface Function Networks for Clothed Human Bodies
Burov, A., Nießner, M., Thies, J.
In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages: 10734-10744, IEEE/CVF International Conference on Computer Vision (ICCV 2021), October 2021 (inproceedings)
We present a novel method for temporal coherent reconstruction and tracking of clothed humans. Given a monocular RGB-D sequence, we learn a person-specific body model which is based on a dynamic surface function network. To this end, we explicitly model the surface of the person using a multi-layer perceptron (MLP) which is embedded into the canonical space of the SMPL body model. With classical forward rendering, the represented surface can be rasterized using the topology of a template mesh. For each surface point of the template mesh, the MLP is evaluated to predict the actual surface location. To handle pose-dependent deformations, the MLP is conditioned on the SMPL pose parameters. We show that this surface representation as well as the pose parameters can be learned in a self-supervised fashion using the principle of analysis-by-synthesis and differentiable rasterization. As a result, we are able to reconstruct a temporally coherent mesh sequence from the input data. The underlying surface representation can be used to synthesize new animations of the reconstructed person including pose-dependent deformations.
Neural Parametric Models for 3D Deformable Shapes
Palafox, P., Bozic, A., Thies, J., Nießner, M., Dai, A.
In 2021 IEEE/CVF International Conference on Computer Vision (ICCV 2021) , pages: 12675-12685 , IEEE, IEEE/CVF International Conference on Computer Vision (ICCV 2021) , October 2021 (inproceedings)
Parametric 3D models have enabled a wide variety of tasks in computer graphics and vision, such as modeling human bodies, faces, and hands. However, the construction of these parametric models is often tedious, as it requires heavy manual tweaking, and they struggle to represent additional complexity and details such as wrinkles or clothing. To this end, we propose Neural Parametric Models (NPMs), a novel, learned alternative to traditional, parametric 3D models, which does not require hand-crafted, object-specific constraints. In particular, we learn to disentangle 4D dynamics into latent-space representations of shape and pose, leveraging the flexibility of recent developments in learned implicit functions. Crucially, once learned, our neural parametric models of shape and pose enable optimization over the learned spaces to fit to new observations, similar to the fitting of a traditional parametric model, e.g., SMPL. This enables NPMs to achieve a significantly more accurate and detailed representation of observed deformable sequences. We show that NPMs improve notably over both parametric and non-parametric state of the art in reconstruction and tracking of monocular depth sequences of clothed humans and hands. Latent-space interpolation as well as shape/pose transfer experiments further demonstrate the usefulness of NPMs.
ID-Reveal: Identity-aware DeepFake Video Detection
Cozzolino, D., Rössler, A., Thies, J., Nießner, M., Verdoliva, L.
In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages: 15088-15097 , IEEE/CVF International Conference on Computer Vision (ICCV 2021), October 2021 (inproceedings)
State-of-the-art DeepFake forgery detectors are trained in a supervised fashion to answer the question ‘is this video real or fake?’. Given that their training is typically method-specific, these approaches show poor generalization across different types of facial manipulations, e.g., face swapping or facial reenactment. In this work, we look at the problem from a different perspective by focusing on the facial characteristics of a specific identity; i.e., we want to answer the question ‘Is this the person who is claimed to be?’. To this end, we introduce ID-Reveal, a new approach that learns temporal facial features, specific of how each person moves while talking, by means of metric learning coupled with an adversarial training strategy. ur method is independent of the specific type of manipulation since it is trained only on real videos. Moreover, relying on high-level semantic features, it is robust to widespread and disruptive forms of post-processing. We performed a thorough experimental analysis on several publicly available benchmarks, such as FaceForensics++, Google’s DFD, and Celeb-DF. Compared to state of the art, our method improves generalization and is more robust to low-quality videos, that are usually spread over social networks. In particular, we obtain an average improvement of more than 15% in terms of accuracy for facial reenactment on high compressed videos.
RetrievalFuse: Neural 3D Scene Reconstruction with a Database
Siddiqui, Y., Thies, J., Ma, F., Shan, Q., Nießner, M., Dai, A.
In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages: 12548-12557 , IEEE/CVF International Conference on Computer Vision (ICCV 2021), October 2021 (inproceedings)
3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks. In contrast to traditional generative learned models which encode the full generative process into a neural network and can struggle with maintaining local details at the scene level, we introduce a new method that directly leverages scene geometry from the training database. First, we learn to synthesize an initial estimate for a 3D scene, constructed by retrieving a top-k set of volumetric chunks from the scene database. These candidates are then refined to a final scene generation with an attention-based refinement that can effectively select the most consistent set of geometry from the candidates and combine them together to create an output scene, facilitating transfer of coherent structures and local detail from train scene geometry. We demonstrate our neural scene reconstruction with a database for the tasks of 3D super-resolution and surface reconstruction from sparse point clouds, showing that our approach enables generation of more coherent, accurate 3D scenes, improving on average by over 8% in IoU over state-of-the-art scene reconstruction.
SpoC: Spoofing Camera Fingerprints
Cozzolino, D., Thies, J., Rössler, A., Nießner, M., Verdoliva, L.
In Workshop on Media Forensics (CVPR 2021), 2021 (inproceedings)
Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction
Bozic, A., Palafox, P., Zollöfer, M., Thies, J., Dai, A., Nießner, M.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 1450-1459 , IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021), 2021 (inproceedings)
We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects. Specifically, we implicitly model a deformation graph via a deep neural network. This neural deformation graph does not rely on any object-specific structure and, thus, can be applied to general non-rigid deformation tracking. Our method globally optimizes this neural graph on a given sequence of depth camera observations of a non-rigidly moving object. Based on explicit viewpoint consistency as well as inter-frame graph and surface consistency constraints, the underlying network is trained in a self-supervised fashion. We additionally optimize for the geometry of the object with an implicit deformable multi-MLP shape representation. Our approach does not assume sequential input data, thus enabling robust tracking of fast motions or even temporally disconnected recordings. Our experiments demonstrate that our Neural Deformation Graphs outperform state-of-the-art non-rigid reconstruction approaches both qualitatively and quantitatively, with 64% improved reconstruction and 62% improved deformation tracking performance.
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction
Gafni, G., Thies, J., Zollöfer, M., Nießner, M.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), CVPR 2021, 2021 (inproceedings)
We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. To handle the dynamics of the face, we combine our scene representation network with a low-dimensional morphable model which provides explicit control over pose and expressions. We use volumetric rendering to generate images from this hybrid representation and demonstrate that such a dynamic neural scene representation can be learned from monocular input data only, without the need of a specialized capture setup.
TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
Bozic, A., Palafox, P., Thies, J., Dai, A., Nießner, M.
Advances in Neural Information Processing Systems 34 (NeurIPS 2021) , 2, pages: 1403-1414 , 35th Conference on Neural Information Processing Systems , 2021 (conference)
We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid representing the scene; this feature grid is then decoded into an implicit 3D scene representation. Key to our approach is the transformer architecture that enables the network to learn to attend to the most relevant image frames for each 3D location in the scene, supervised only by the scene reconstruction task. Features are fused in a coarse-to-fine fashion, storing fine-level features only where needed, requiring lower memory storage and enabling fusion at interactive rates. The feature grid is then decoded to a higher-resolution scene reconstruction, using an MLP-based surface occupancy prediction from interpolated coarse-to-fine 3D features. Our approach results in an accurate surface reconstruction, outperforming state-of-the-art multi-view stereo depth estimation methods, fully-convolutional 3D reconstruction approaches, and approaches using LSTM- or GRU-based recurrent networks for video sequence fusion.
SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans
Dai, A., Siddiqui, Y., Thies, J., Valentin, J., Nießner, M.
In IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), CVPR 2021, 2021 (inproceedings)
We present Self-Supervised Photometric Scene Generation (SPSG), a novel approach to generate high-quality, colored 3D models of scenes from RGB-D scan observations by learning to infer unobserved scene geometry and color in a self-supervised fashion. Our self-supervised approach learns to jointly inpaint geometry and color by correlating an incomplete RGB-D scan with a more complete version of that scan. Notably, rather than relying on 3D reconstruction losses to inform our 3D geometry and color reconstruction, we propose adversarial and perceptual losses operating on 2D renderings in order to achieve high-resolution, high-quality colored reconstructions of scenes. This exploits the high-resolution, self-consistent signal from individual raw RGB-D frames, in contrast to fused 3D reconstructions of the frames which exhibit inconsistencies from view-dependent effects, such as color balancing or pose inconsistencies. Thus, by informing our 3D scene generation directly through 2D signal, we produce high-quality colored reconstructions of 3D scenes, outperforming state of the art on both synthetic and real data.
Neural RGB-D Surface Reconstruction
Azinovic, D., Martin-Brualla, R., Goldman, D. B., Nießner, M., Thies, J.
ArXiv, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages: 6280-6291 , IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022), 2021 (conference)
2020
Neural Voice Puppetry: Audio-driven Facial Reenactment
Thies, J., Elgharib, M., Tewari, A., Theobalt, C., Nießner, M.
In Computer Vision – ECCV 2020, Springer International Publishing, Cham, August 2020 (inproceedings)
We present Neural Voice Puppetry, a novel approach for audio-driven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photo-realistic output video of a target person that is in sync with the audio of the source input. This audio-driven facial reenactment is driven by a deep neural network that employs a latent 3D face model space. Through the underlying 3D representation, the model inherently learns temporal stability while we leverage neural rendering to generate photo-realistic output frames. Our approach generalizes across different people, allowing us to synthesize videos of a target actor with the voice of any unknown source actor or even synthetic voices that can be generated utilizing standard text-to-speech approaches. Neural Voice Puppetry has a variety of use-cases, including audio-driven video avatars, video dubbing, and text-driven video synthesis of a talking head. We demonstrate the capabilities of our method in a series of audio- and text-based puppetry examples. Our method is not only more general than existing works since we are generic to the input person, but we also show superior visual and lip sync quality compared to photo-realistic audio- and video-driven reenactment techniques.
Adversarial Texture Optimization from RGB-D Scans
Huang, J., Thies, J., Dai, A., Kundu, A., Jiang, C., Guibas, L., Nießner, M., Funkhouser, T.
In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020, 2020 (inproceedings)
Realistic color texture generation is an important step in RGB-D surface reconstruction, but remains challenging in practice due to inaccuracies in reconstructed geometry, misaligned camera poses, and view-dependent imaging artifacts. In this work, we present a novel approach for color texture generation using a conditional adversarial loss obtained from weakly-supervised views. Specifically, we propose an approach to produce photorealistic textures for approximate surfaces, even from misaligned images, by learning an objective function that is robust to these errors. The key idea of our approach is to learn a patch-based conditional discriminator which guides the texture optimization to be tolerant to misalignments. Our discriminator takes a synthesized view and a real image, and evaluates whether the synthesized one is realistic, under a broadened definition of realism. We train the discriminator by providing as ‘real’ examples pairs of input views and their misaligned versions – so that the learned adversarial loss will tolerate errors from the scans. Experiments on synthetic and real data under quantitative or qualitative evaluation demonstrate the advantage of our approach in comparison to state of the art.
Neural Non-Rigid Tracking
Bozic, A., Palafox, P., Zollöfer, M., Dai, A., Thies, J., Nießner, M.
In NeurIPS, 2020 (inproceedings)
We introduce a novel, end-to-end learnable, differentiable non-rigid tracker that enables state-of-the-art non-rigid reconstruction. Given two input RGB-D frames of a non-rigidly moving object, we employ a convolutional neural network to predict dense correspondences. These correspondences are used as constraints in an as-rigid-as-possible (ARAP) optimization problem. By enabling gradient back-propagation through the non-rigid optimization solver, we are able to learn correspondences in an end-to-end manner such that they are optimal for the task of non-rigid tracking. Furthermore, this formulation allows for learning correspondence weights in a self-supervised manner. Thus, outliers and wrong correspondences are down-weighted to enable robust tracking. Compared to state-of-the-art approaches, our algorithm shows improved reconstruction performance, while simultaneously achieving 85x faster correspondence prediction than comparable deep-learning based methods.
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
Alhaija, H. A., Mustikovela, S. K., Thies, J., Nießner, M., Geiger, A., Rother, C.
3DV, 2020 (conference)
Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been proposed for this task, acquiring a dataset of images with accurately aligned 3D models is very difficult. The main contribution of this work is to lift this restriction by training a neural rendering algorithm from unpaired data. More specifically, we propose an autoencoder for joint generation of realistic images from synthetic 3D models while simultaneously decomposing real images into their intrinsic shape and appearance properties. In contrast to a traditional graphics pipeline, our approach does not require to specify all scene properties, such as material parameters and lighting by hand. Instead, we learn photo-realistic deferred rendering from a small set of 3D models and a larger set of unaligned real images, both of which are easy to acquire in practice. Simultaneously, we obtain accurate intrinsic decompositions of real images while not requiring paired ground truth. Our experiments confirm that a joint treatment of rendering and decomposition is indeed beneficial and that our approach outperforms state-of-the-art image-toimage translation baselines both qualitatively and quantitatively.
State of the Art on Neural Rendering
Tewari, A., Fried, O., Thies, J., Sitzmann, V., Lombardi, S., Sunkavalli, K., Martin-Brualla, R., Simon, T., Saragih, J., Nießner, M., Pandey, R., Fanello, S., Wetzstein, G., Zhu, J., Theobalt, C., Agrawala, M., Shechtman, E., Goldman, D. B., Zollhöfer, M.
In EG, 2020 (inproceedings)
Efficient rendering of photo-realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo-realistic images from hand-crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo-realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state-of-the-art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photo-realistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. Specifically, our emphasis is on the type of control, i.e., how the control is provided, which parts of the pipeline are learned, explicit vs.~implicit control, generalization, and stochastic vs.~deterministic synthesis. The second half of this state-of-the-art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free-viewpoint video, and the creation of photo-realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems.
2019
DeepVoxels: Learning Persistent 3D Feature Embeddings
Sitzmann, V., Thies, J., Heide, F., Nießner, M., Wetzstein, G., Zollhöfer,
In Proc. Computer Vision and Pattern Recognition (CVPR), IEEE, 2019 (inproceedings)
In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the view-dependent appearance of a 3D object without having to explicitly model its geometry. At its core, our approach is based on a Cartesian 3D grid of persistent embedded features that learn to make use of the underlying 3D scene structure. Our approach thus combines insights from 3D geometric computer vision with recent advances in learning image-to-image mappings based on adversarial loss functions. DeepVoxels is supervised, without requiring a 3D reconstruction of the scene, using a 2D re-rendering loss and enforces perspective and multi-view geometry in a principled manner. We apply our persistent 3D scene representation to the problem of novel view synthesis demonstrating high-quality results for a variety of challenging objects.
FaceForensics++: Learning to Detect Manipulated Facial Images
Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nießner, M.
In ICCV 2019, 2019 (inproceedings)
The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false information or fake news. This paper examines the realism of state-of-the-art image manipulations, and how difficult it is to detect them, either automatically or by humans. To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on DeepFakes, Face2Face, FaceSwap and NeuralTextures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. This dataset is over an order of magnitude larger than comparable, publicly available, forgery datasets. Based on this data, we performed a thorough analysis of data-driven forgery detectors. We show that the use of additional domain specific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.
2018
InverseFaceNet: Deep Monocular Inverse Face Rendering
Kim, H., Zollhöfer, M., Tewari, A., Thies, J., Richardt, C., Theobalt, C.
In Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (inproceedings)
We introduce InverseFaceNet, a deep convolutional inverse rendering framework for faces that jointly estimates facial pose, shape, expression, reflectance and illumination from a single input image. By estimating all parameters from just a single image, advanced editing possibilities on a single face image, such as appearance editing and relighting, become feasible in real time. Most previous learning-based face reconstruction approaches do not jointly recover all dimensions, or are severely limited in terms of visual quality. In contrast, we propose to recover high-quality facial pose, shape, expression, reflectance and illumination using a deep neural network that is trained using a large, synthetically created training corpus. Our approach builds on a novel loss function that measures model-space similarity directly in parameter space and significantly improves reconstruction accuracy. We further propose a self-supervised bootstrapping process in the network training loop, which iteratively updates the synthetic training corpus to better reflect the distribution of real-world imagery. We demonstrate that this strategy outperforms completely synthetically trained networks. Finally, we show high-quality reconstructions and compare our approach to several state-of-the-art approaches.
2017
Face2Face: Real-time Facial Reenactment
In Eurographics Digital Library - Online Dissertations, 2017 (inproceedings)
In this dissertation we show our advances in the field of 3D reconstruction of human faces using commodity hardware. Beside the reconstruction of the facial geometry and texture, real-time face tracking is demonstrated. The developed algorithms are based on the principle of analysis-by-synthesis. To apply this principle, a mathematical model that represents a face virtually is defined. In addition to the face, the sensor observation process of the used camera is modeled. Utilizing this model to synthesize facial imagery, the model parameters are adjusted, such that the synthesized image fits the input image as good as possible. Thus, in reverse, this process transfers the input image to a virtual representation of the face. The achieved quality allows many new applications that require a good reconstruction of the face. One of these applications is the so-called ‘‘Facial Reenactment’’. Our developed methods show that such an application does not need any special hardware. The generated results are nearly photo-realistic videos that show the transfer of the mimic of one person to another person. These techniques can for example be used to bring movie dubbing to a new level. Instead of adapting the audio to the video, which might also include changes of the text, the video can be post-processed to match the mouth movements of the dubber. Since the approaches that we show in this dissertation run in real-time, one can also think of a live dubber in a video teleconferencing system that simultaneously translates the speech of a person to another language. The published videos of our projects in this dissertation led to a broad discussion in the media. On the one hand this is due to the fact that our methods are designed such that they run in real-time and on the other hand that we reduced the hardware requirements to a minimum. In fact, after some preprocessing, we are able to edit ordinary videos from the Internet in real-time. Amongst others, we impose a different mimic to faces of prominent persons like former presidents of the United States of America. This led inevitably to a discussion about trustworthiness of video material, especially from unknown source. Most people did not expect that such manipulations are possible, neglecting existing methods that are already able to edit videos (e.g. special effects in movie productions). Thus, beside the advances in real-time face tracking, our projects raised the awareness of video manipulation.
FaceForge: Markerless Non-Rigid Face Multi-Projection Mapping
Siegl, C., Lange, V., Stamminger, M., Bauer, F., Thies, J.
In IEEE Transactions on Visualization & Computer Graphics, 2017 (inproceedings)
Recent publications and art performances demonstrate amazing results using projection mapping. To our knowledge, there exists no multi-projection system that can project onto non-rigid target geometries. This constrains the applicability and quality for live performances with multiple spectators. Given the cost and complexity of current systems, we present a low-cost easy-to-use markerless non-rigid face multi-projection system. It is based on a non-rigid, dense face tracker and a real-time multi-projection solver adapted to imprecise tracking, geometry and calibration. Using this novel system we produce compelling results with only consumer-grade hardware.
2016
Face2Face: Real-time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhöfer, M., Stamminger, M., Theobalt, C., Nießner, M.
In Proc. Computer Vision and Pattern Recognition (CVPR), IEEE, 2016 (inproceedings)
We present a novel approach for real-time facial reenactment of a monocular target video sequence (e.g., Youtube video). The source sequence is also a monocular video stream, captured live with a commodity webcam. Our goal is to animate the facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. To this end, we first address the under-constrained problem of facial identity recovery from monocular video by non-rigid model-based bundling. At run time, we track facial expressions of both source and target video using a dense photometric consistency measure. Reenactment is then achieved by fast and efficient deformation transfer between source and target. The mouth interior that best matches the re-targeted expression is retrieved from the target sequence and warped to produce an accurate fit. Finally, we convincingly re-render the synthesized target face on top of the corresponding video stream such that it seamlessly blends with the real-world illumination. We demonstrate our method in a live setup, where Youtube videos are reenacted in real time.
