Search

Real-time rendering of human head avatars is a cornerstone of many computer graphics applications, such as augmented reality, video games, and films, to name a few. Recent approaches address this challenge with computationally efficient geometry primitives in a carefully calibrated multi-view setup. Albeit producing photorealistic head renderings, it often fails to represent complex motion changes such as the mouth interior and strongly varying head poses. We propose a new method to generate highly dynamic and deformable human head avatars from multi-view imagery in real-time. At the core of our method is a hierarchical representation of head models that allows to capture the complex dynamics of facial expressions and head movements. First, with rich facial features extracted from raw input frames, we learn to deform the coarse facial geometry of the template mesh. We then initialize 3D Gaussians on the deformed surface and refine their positions in a fine step. We train this coarse-to-fine facial avatar model along with the head pose as a learnable parameter in an end-to-end framework. This enables not only controllable facial animation via video inputs, but also high-fidelity novel view synthesis of challenging facial expressions, such as tongue deformations and fine-grained teeth structure under large motion changes. Moreover, it encourages the learned head avatar to generalize towards new facial expressions and head poses at inference time. We demonstrate the performance of our method with comparisons against the related methods on different datasets, spanning challenging facial expression sequences across multiple identities. We also show the potential application of our approach by demonstrating a cross-identity facial performance transfer application., Comment: ACM Transaction on Graphics (SIGGRAPH Asia 2024); Project page: https://vcai.mpi-inf.mpg.de/projects/GaussianHeads/

Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency, coupled with inaccuracies in physically realistic lighting and identity preservation. Furthermore, personalization from a single view is difficult to achieve and often requires multiview images during the testing phase or involves slow optimization processes. This paper introduces Lite2Relight, a novel technique that can predict 3D consistent head poses of portraits while performing physically plausible light editing at interactive speed. Our method uniquely extends the generative capabilities and efficient volumetric representation of EG3D, leveraging a lightstage dataset to implicitly disentangle face reflectance and perform relighting under target HDRI environment maps. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space, enhancing them with a strong face geometry and reflectance prior. Through extensive quantitative and qualitative evaluations, we show that our method outperforms the state-of-the-art methods in terms of efficacy, photorealism, and practical application. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions. Lite2Relight paves the way for large-scale adoption of photorealistic portrait editing in various domains, offering a robust, interactive solution to a previously constrained problem. Project page: https://vcai.mpi-inf.mpg.de/projects/Lite2Relight/, Comment: Accepted at SIGGRAPH '24: ACM SIGGRAPH 2024 Conference Papers

Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous tokens. However, video streaming remains much less explored, despite a growing need for live video processing. State-of-the-art video diffusion models leverage bi-directional temporal attention to model the correlations between the current frame and all the surrounding (i.e. including future) frames, which hinders them from processing streaming videos. To address this problem, we present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation. Compared to previous works, our approach ensures temporal consistency and smoothness by correlating the current frame with its predecessors and a few initial warmup frames, without any future frames. Additionally, we use a highly efficient denoising scheme featuring a KV-cache mechanism and pipelining, to facilitate streaming video translation at interactive framerates. Extensive experiments demonstrate the effectiveness of the proposed attention mechanism and pipeline, outperforming previous methods in terms of temporal smoothness and/or efficiency., Comment: https://live2diff.github.io/

Capturing and editing full head performances enables the creation of virtual characters with various applications such as extended reality and media production. The past few years witnessed a steep rise in the photorealism of human head avatars. Such avatars can be controlled through different input data modalities, including RGB, audio, depth, IMUs and others. While these data modalities provide effective means of control, they mostly focus on editing the head movements such as the facial expressions, head pose and/or camera viewpoint. In this paper, we propose AvatarStudio, a text-based method for editing the appearance of a dynamic full head avatar. Our approach builds on existing work to capture dynamic performances of human heads using neural radiance field (NeRF) and edits this representation with a text-to-image diffusion model. Specifically, we introduce an optimization strategy for incorporating multiple keyframes representing different camera viewpoints and time stamps of a video performance into a single diffusion model. Using this personalized diffusion model, we edit the dynamic NeRF by introducing view-and-time-aware Score Distillation Sampling (VT-SDS) following a model-based guidance approach. Our method edits the full head in a canonical space, and then propagates these edits to remaining time steps via a pretrained deformation network. We evaluate our method visually and numerically via a user study, and results show that our method outperforms existing approaches. Our experiments validate the design choices of our method and highlight that our edits are genuine, personalized, as well as 3D- and time-consistent., Comment: 17 pages, 17 figures. Project page: https://vcai.mpi-inf.mpg.de/projects/AvatarStudio/

Advances in 3D-aware generative models have pushed the boundary of image synthesis with explicit camera control. To achieve high-resolution image synthesis, several attempts have been made to design efficient generators, such as hybrid architectures with both 3D and 2D components. However, such a design compromises multiview consistency, and the design of a pure 3D generator with high resolution is still an open problem. In this work, we present Generative Volumetric Primitives (GVP), the first pure 3D generative model that can sample and render 512-resolution images in real-time. GVP jointly models a number of volumetric primitives and their spatial information, both of which can be efficiently generated via a 2D convolutional network. The mixture of these primitives naturally captures the sparsity and correspondence in the 3D volume. The training of such a generator with a high degree of freedom is made possible through a knowledge distillation technique. Experiments on several datasets demonstrate superior efficiency and 3D consistency of GVP over the state-of-the-art., Comment: https://vcai.mpi-inf.mpg.de/projects/GVP/index.html

Multi-view volumetric rendering techniques have recently shown great potential in modeling and synthesizing high-quality head avatars. A common approach to capture full head dynamic performances is to track the underlying geometry using a mesh-based template or 3D cube-based graphics primitives. While these model-based approaches achieve promising results, they often fail to learn complex geometric details such as the mouth interior, hair, and topological changes over time. This paper presents a novel approach to building highly photorealistic digital head avatars. Our method learns a canonical space via an implicit function parameterized by a neural network. It leverages multiresolution hash encoding in the learned feature space, allowing for high-quality, faster training and high-resolution rendering. At test time, our method is driven by a monocular RGB video. Here, an image encoder extracts face-specific features that also condition the learnable canonical space. This encourages deformation-dependent texture variations during training. We also propose a novel optical flow based loss that ensures correspondences in the learned canonical space, thus encouraging artifact-free and temporally consistent renderings. We show results on challenging facial expressions and show free-viewpoint renderings at interactive real-time rates for medium image resolutions. Our method outperforms all existing approaches, both visually and numerically. We will release our multiple-identity dataset to encourage further research. Our Project page is available at: https://vcai.mpi-inf.mpg.de/projects/HQ3DAvatar/, Comment: 16 Pages, 15 Figures. Project page: https://vcai.mpi-inf.mpg.de/projects/HQ3DAvatar/

The human hand is the main medium through which we interact with our surroundings, making its digitization an important problem. While there are several works modeling the geometry of hands, little attention has been paid to capturing photo-realistic appearance. Moreover, for applications in extended reality and gaming, real-time rendering is critical. We present the first neural-implicit approach to photo-realistically render hands in real-time. This is a challenging problem as hands are textured and undergo strong articulations with pose-dependent effects. However, we show that this aim is achievable through our carefully designed method. This includes training on a low-resolution rendering of a neural radiance field, together with a 3D-consistent super-resolution module and mesh-guided sampling and space canonicalization. We demonstrate a novel application of perceptual loss on the image space, which is critical for learning details accurately. We also show a live demo where we photo-realistically render the human hand in real-time for the first time, while also modeling pose- and view-dependent appearance effects. We ablate all our design choices and show that they optimize for rendering speed and quality. Video results and our code can be accessed from https://vcai.mpi-inf.mpg.de/projects/LiveHand/, Comment: Project page: https://vcai.mpi-inf.mpg.de/projects/LiveHand/ | Accepted at ICCV '23 | 11 pages, 7 figures

3D Morphable models of the human body capture variations among subjects and are useful in reconstruction and editing applications. Current dental models use an explicit mesh scene representation and model only the teeth, ignoring the gum. In this work, we present the first parametric 3D morphable dental model for both teeth and gum. Our model uses an implicit scene representation and is learned from rigidly aligned scans. It is based on a component-wise representation for each tooth and the gum, together with a learnable latent code for each of such components. It also learns a template shape thus enabling several applications such as segmentation, interpolation, and tooth replacement. Our reconstruction quality is on par with the most advanced global implicit representations while enabling novel applications. Project page: https://vcai.mpi-inf.mpg.de/projects/DMM/

3D generative models of objects enable photorealistic image synthesis with 3D control. Existing methods model the scene as a global scene representation, ignoring the compositional aspect of the scene. Compositional reasoning can enable a wide variety of editing applications, in addition to enabling generalizable 3D reasoning. In this paper, we present a compositional generative model, where each semantic part of the object is represented as an independent 3D representation learned from only in-the-wild 2D data. We start with a global generative model (GAN) and learn to decompose it into different semantic parts using supervision from 2D segmentation masks. We then learn to composite independently sampled parts in order to create coherent global scenes. Different parts can be independently sampled while keeping the rest of the object fixed. We evaluate our method on a wide variety of objects and parts and demonstrate editing applications., Comment: https://vcai.mpi-inf.mpg.de/projects/gCoRF/

Asynchronously operating event cameras find many applications due to their high dynamic range, vanishingly low motion blur, low latency and low data bandwidth. The field saw remarkable progress during the last few years, and existing event-based 3D reconstruction approaches recover sparse point clouds of the scene. However, such sparsity is a limiting factor in many cases, especially in computer vision and graphics, that has not been addressed satisfactorily so far. Accordingly, this paper proposes the first approach for 3D-consistent, dense and photorealistic novel view synthesis using just a single colour event stream as input. At its core is a neural radiance field trained entirely in a self-supervised manner from events while preserving the original resolution of the colour event channels. Next, our ray sampling strategy is tailored to events and allows for data-efficient training. At test, our method produces results in the RGB space at unprecedented quality. We evaluate our method qualitatively and numerically on several challenging synthetic and real scenes and show that it produces significantly denser and more visually appealing renderings than the existing methods. We also demonstrate robustness in challenging scenarios with fast motion and under low lighting conditions. We release the newly recorded dataset and our source code to facilitate the research field, see https://4dqv.mpi-inf.mpg.de/EventNeRF., Comment: 19 pages, 21 figures, 3 tables; CVPR 2023

Shape-from-Template (SfT) methods estimate 3D surface deformations from a single monocular RGB camera while assuming a 3D state known in advance (a template). This is an important yet challenging problem due to the under-constrained nature of the monocular setting. Existing SfT techniques predominantly use geometric and simplified deformation models, which often limits their reconstruction abilities. In contrast to previous works, this paper proposes a new SfT approach explaining 2D observations through physical simulations accounting for forces and material properties. Our differentiable physics simulator regularises the surface evolution and optimises the material elastic properties such as bending coefficients, stretching stiffness and density. We use a differentiable renderer to minimise the dense reprojection error between the estimated 3D states and the input images and recover the deformation parameters using an adaptive gradient-based optimisation. For the evaluation, we record with an RGB-D camera challenging real surfaces exposed to physical forces with various material properties and textures. Our approach significantly reduces the 3D reconstruction error compared to multiple competing methods. For the source code and data, see https://4dqv.mpi-inf.mpg.de/phi-SfT/., Comment: 11 pages, 8 figures and one table; Computer Vision and Pattern Recognition (CVPR) 2022

Photorealistic editing of outdoor scenes from photographs requires a profound understanding of the image formation process and an accurate estimation of the scene geometry, reflectance and illumination. A delicate manipulation of the lighting can then be performed while keeping the scene albedo and geometry unaltered. We present NeRF-OSR, i.e., the first approach for outdoor scene relighting based on neural radiance fields. In contrast to the prior art, our technique allows simultaneous editing of both scene illumination and camera viewpoint using only a collection of outdoor photos shot in uncontrolled settings. Moreover, it enables direct control over the scene illumination, as defined through a spherical harmonics model. For evaluation, we collect a new benchmark dataset of several outdoor sites photographed from multiple viewpoints and at different times. For each time, a 360 degree environment map is captured together with a colour-calibration chequerboard to allow accurate numerical evaluations on real data against ground truth. Comparisons against SoTA show that NeRF-OSR enables controllable lighting and viewpoint editing at higher quality and with realistic self-shadowing reproduction. Our method and the dataset are publicly available at https://4dqv.mpi-inf.mpg.de/NeRF-OSR/., Comment: 22 pages, 10 figures, 2 tables; ECCV 2022; project web page: https://4dqv.mpi-inf.mpg.de/NeRF-OSR/

Generative adversarial models (GANs) continue to produce advances in terms of the visual quality of still images, as well as the learning of temporal correlations. However, few works manage to combine these two interesting capabilities for the synthesis of video content: Most methods require an extensive training dataset to learn temporal correlations, while being rather limited in the resolution and visual quality of their output. We present a novel approach to the video synthesis problem that helps to greatly improve visual quality and drastically reduce the amount of training data and resources necessary for generating videos. Our formulation separates the spatial domain, in which individual frames are synthesized, from the temporal domain, in which motion is generated. For the spatial domain we use a pre-trained StyleGAN network, the latent space of which allows control over the appearance of the objects it was trained for. The expressive power of this model allows us to embed our training videos in the StyleGAN latent space. Our temporal architecture is then trained not on sequences of RGB frames, but on sequences of StyleGAN latent codes. The advantageous properties of the StyleGAN space simplify the discovery of temporal correlations. We demonstrate that it suffices to train our temporal architecture on only 10 minutes of footage of 1 subject for about 6 hours. After training, our model can not only generate new portrait videos for the training subject, but also for any random subject which can be embedded in the StyleGAN space., Comment: Final draft

We introduce a method for egocentric videoconferencing that enables hands-free video calls, for instance by people wearing smart glasses or other mixed-reality devices. Videoconferencing portrays valuable non-verbal communication and face expression cues, but usually requires a front-facing camera. Using a frontal camera in a hands-free setting when a person is on the move is impractical. Even holding a mobile phone camera in the front of the face while sitting for a long duration is not convenient. To overcome these issues, we propose a low-cost wearable egocentric camera setup that can be integrated into smart glasses. Our goal is to mimic a classical video call, and therefore, we transform the egocentric perspective of this camera into a front facing video. To this end, we employ a conditional generative adversarial neural network that learns a transition from the highly distorted egocentric views to frontal views common in videoconferencing. Our approach learns to transfer expression details directly from the egocentric view without using a complex intermediate parametric expressions model, as it is used by related face reenactment methods. We successfully handle subtle expressions, not easily captured by parametric blendshape-based solutions, e.g., tongue movement, eye movements, eye blinking, strong expressions and depth varying movements. To get control over the rigid head movements in the target view, we condition the generator on synthetic renderings of a moving neutral face. This allows us to synthesis results at different head poses. Our technique produces temporally smooth video-realistic renderings in real-time using a video-to-video translation network in conjunction with a temporal discriminator. We demonstrate the improved capabilities of our technique by comparing against related state-of-the art approaches., Comment: Mohamed Elgharib and Mohit Mendiratta contributed equally to this work. http://gvv.mpi-inf.mpg.de/projects/EgoChat/

Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo. Current techniques are completely supervised, requiring high quality synthetic renderings to train a solution. Such renderings are synthesized using priors learned from limited data. In contrast, we propose a self-supervised approach for relighting. Our approach is trained only on corpora of images collected from the internet without any user-supervision. This virtually endless source of training data allows training a general relighting solution. Our approach first decomposes an image into its albedo, geometry and illumination. A novel relighting is then produced by modifying the illumination parameters. Our solution capture shadow using a dedicated shadow prediction map, and does not rely on accurate geometry estimation. We evaluate our technique subjectively and objectively using a new dataset with ground-truth relighting. Results show the ability of our technique to produce photo-realistic and physically plausible results, that generalizes to unseen scenes., Comment: Published in ECCV '20, http://gvv.mpi-inf.mpg.de/projects/SelfRelight/

This paper introduces the first differentiable simulator of event streams, i.e., streams of asynchronous brightness change signals recorded by event cameras. Our differentiable simulator enables non-rigid 3D tracking of deformable objects (such as human hands, isometric surfaces and general watertight meshes) from event streams by leveraging an analysis-by-synthesis principle. So far, event-based tracking and reconstruction of non-rigid objects in 3D, like hands and body, has been either tackled using explicit event trajectories or large-scale datasets. In contrast, our method does not require any such processing or data, and can be readily applied to incoming event streams. We show the effectiveness of our approach for various types of non-rigid objects and compare to existing methods for non-rigid 3D tracking. In our experiments, the proposed energy-based formulations outperform competing RGB-based methods in terms of 3D errors. The source code and the new data are publicly available., Comment: In CVPR 2021 Workshop on Event-based Vision. Project page: http://gvv.mpi-inf.mpg.de/projects/Event-based_Non-rigid_3D_Tracking

Photorealistic editing of portraits is a challenging task as humans are very sensitive to inconsistencies in faces. We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination in a portrait image. This requires our method to capture and control the full reflectance field of the person in the image. Most editing approaches rely on supervised learning using training data captured with setups such as light and camera stages. Such datasets are expensive to acquire, not readily available and do not capture all the rich variations of in-the-wild portrait images. In addition, most supervised approaches only focus on relighting, and do not allow camera viewpoint editing. Thus, they only capture and control a subset of the reflectance field. Recently, portrait editing has been demonstrated by operating in the generative model space of StyleGAN. While such approaches do not require direct supervision, there is a significant loss of quality when compared to the supervised approaches. In this paper, we present a method which learns from limited supervised training data. The training images only include people in a fixed neutral expression with eyes closed, without much hair or background variations. Each person is captured under 150 one-light-at-a-time conditions and under 8 camera poses. Instead of training directly in the image space, we design a supervised problem which learns transformations in the latent space of StyleGAN. This combines the best of supervised learning and generative adversarial modeling. We show that the StyleGAN prior allows for generalisation to different expressions, hairstyles and backgrounds. This produces high-quality photorealistic results for in-the-wild images and significantly outperforms existing methods. Our approach can edit the illumination and pose simultaneously, and runs at interactive rates., Comment: http://gvv.mpi-inf.mpg.de/projects/PhotoApp/

We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input. Our algorithm uses a CNN architecture that leverages the inherent correlation between facial expression and hand gestures. Synthesis of conversational body gestures is a multi-modal problem since many similar gestures can plausibly accompany the same input speech. To synthesize plausible body gestures in this setting, we train a Generative Adversarial Network (GAN) based model that measures the plausibility of the generated sequences of 3D body motion when paired with the input audio features. We also contribute a new way to create a large corpus of more than 33 hours of annotated body, hand, and face data from in-the-wild videos of talking people. To this end, we apply state-of-the-art monocular approaches for 3D body and hand pose estimation as well as dense 3D face performance capture to the video corpus. In this way, we can train on orders of magnitude more data than previous algorithms that resort to complex in-studio motion capture solutions, and thereby train more expressive synthesis algorithms. Our experiments and user study show the state-of-the-art quality of our speech-synthesized full 3D character animations.

Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing dynamics, including fine and high-frequency details, significantly limits the attainable visual quality. We address these limitations for the first time in the literature and present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations, for several types of loose garments. In contrast to the previous techniques, we perform image generation in three subsequent stages, synthesizing human shape, structure, and appearance. Given a monocular RGB video of an actor, we train a stack of recurrent deep neural networks that generate these intermediate representations from 2D poses and their temporal derivatives. Splitting the difficult motion transfer problem into subtasks that are aware of the temporal motion context helps us to synthesize results with plausible dynamics and pose-dependent detail. It also allows artistic control of results by manipulation of individual framework stages. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism. Our code and data will be made publicly available., Comment: 14 pages, 8 figures; project page: https://graphics.tu-bs.de/publications/kappel2020high-fidelity

3D hand pose estimation from monocular videos is a long-standing and challenging problem, which is now seeing a strong upturn. In this work, we address it for the first time using a single event camera, i.e., an asynchronous vision sensor reacting on brightness changes. Our EventHands approach has characteristics previously not demonstrated with a single RGB or depth camera such as high temporal resolution at low data throughputs and real-time performance at 1000 Hz. Due to the different data modality of event cameras compared to classical cameras, existing methods cannot be directly applied to and re-trained for event streams. We thus design a new neural approach which accepts a new event stream representation suitable for learning, which is trained on newly-generated synthetic event streams and can generalise to real data. Experiments show that EventHands outperforms recent monocular methods using a colour (or depth) camera in terms of accuracy and its ability to capture hand motions of unprecedented speed. Our method, the event stream simulator and the dataset are publicly available; see https://4dqv.mpi-inf.mpg.de/EventHands/, Comment: 16 pages, 10 figures, 1 table; project page: https://4dqv.mpi-inf.mpg.de/EventHands/

We present the first deep implicit 3D morphable model (i3DMM) of full heads. Unlike earlier morphable face models it not only captures identity-specific geometry, texture, and expressions of the frontal face, but also models the entire head, including hair. We collect a new dataset consisting of 64 people with different expressions and hairstyles to train i3DMM. Our approach has the following favorable properties: (i) It is the first full head morphable model that includes hair. (ii) In contrast to mesh-based models it can be trained on merely rigidly aligned scans, without requiring difficult non-rigid registration. (iii) We design a novel architecture to decouple the shape model into an implicit reference shape and a deformation of this reference shape. With that, dense correspondences between shapes can be learned implicitly. (iv) This architecture allows us to semantically disentangle the geometry and color components, as color is learned in the reference space. Geometry is further disentangled as identity, expressions, and hairstyle, while color is disentangled as identity and hairstyle components. We show the merits of i3DMM using ablation studies, comparisons to state-of-the-art models, and applications such as semantic head editing and texture transfer. We will make our model publicly available., Comment: Project page: http://gvv.mpi-inf.mpg.de/projects/i3DMM/

Most 3D face reconstruction methods rely on 3D morphable models, which disentangle the space of facial deformations into identity geometry, expressions and skin reflectance. These models are typically learned from a limited number of 3D scans and thus do not generalize well across different identities and expressions. We present the first approach to learn complete 3D models of face identity geometry, albedo and expression just from images and videos. The virtually endless collection of such data, in combination with our self-supervised learning-based approach allows for learning face models that generalize beyond the span of existing approaches. Our network design and loss functions ensure a disentangled parameterization of not only identity and albedo, but also, for the first time, an expression basis. Our method also allows for in-the-wild monocular reconstruction at test time. We show that our learned models better generalize and lead to higher quality image-based reconstructions than existing approaches., Comment: Project Page - https://gvv.mpi-inf.mpg.de/projects/LeMoMo

Editing of portrait images is a very popular and important research topic with a large variety of applications. For ease of use, control should be provided via a semantically meaningful parameterization that is akin to computer animation controls. The vast majority of existing techniques do not provide such intuitive and fine-grained control, or only enable coarse editing of a single isolated control parameter. Very recently, high-quality semantically controlled editing has been demonstrated, however only on synthetically created StyleGAN images. We present the first approach for embedding real portrait images in the latent space of StyleGAN, which allows for intuitive editing of the head pose, facial expression, and scene illumination in the image. Semantic editing in parameter space is achieved based on StyleRig, a pretrained neural network that maps the control space of a 3D morphable face model to the latent space of the GAN. We design a novel hierarchical non-linear optimization problem to obtain the embedding. An identity preservation energy term allows spatially coherent edits while maintaining facial integrity. Our approach runs at interactive frame rates and thus allows the user to explore the space of possible edits. We evaluate our approach on a wide set of portrait photos, compare it to the current state of the art, and validate the effectiveness of its components in an ablation study., Comment: To appear in SIGGRAPH Asia 2020. Project webpage: https://gvv.mpi-inf.mpg.de/projects/PIE/

Reflections in videos are obstructions that often occur when videos are taken behind reflective surfaces like glass. These reflections reduce the quality of such videos, lead to information loss and degrade the accuracy of many computer vision algorithms. A video containing reflections is a combination of background and reflection layers. Thus, reflection removal is equivalent to decomposing the video into two layers. This, however, is a challenging and ill-posed problem as there is an infinite number of valid decompositions. To address this problem, we propose a user-assisted method for video reflection removal. We rely on both spatial and temporal information and utilize sparse user hints to help improve separation. The key idea of the proposed method is to use motion cues to separate the background layer from the reflection layer with minimal user assistance. We show that user-assistance significantly improves the layer separation results. We implement and evaluate the proposed method through quantitative and qualitative results on real and synthetic videos. Our experiments show that the proposed method successfully removes reflection from video sequences, does not introduce visual distortions, and significantly outperforms the state-of-the-art reflection removal methods in the literature.

The reflectance field of a face describes the reflectance properties responsible for complex lighting effects including diffuse, specular, inter-reflection and self shadowing. Most existing methods for estimating the face reflectance from a monocular image assume faces to be diffuse with very few approaches adding a specular component. This still leaves out important perceptual aspects of reflectance as higher-order global illumination effects and self-shadowing are not modeled. We present a new neural representation for face reflectance where we can estimate all components of the reflectance responsible for the final appearance from a single monocular image. Instead of modeling each component of the reflectance separately using parametric models, our neural representation allows us to generate a basis set of faces in a geometric deformation-invariant space, parameterized by the input light direction, viewpoint and face geometry. We learn to reconstruct this reflectance field of a face just from a monocular image, which can be used to render the face from any viewpoint in any light condition. Our method is trained on a light-stage training dataset, which captures 300 people illuminated with 150 light conditions from 8 viewpoints. We show that our method outperforms existing monocular reflectance reconstruction methods, in terms of photorealism due to better capturing of physical premitives, such as sub-surface scattering, specularities, self-shadows and other higher-order effects., Comment: Project page - http://gvv.mpi-inf.mpg.de/projects/FaceReflectanceFields/

There are concerns that new approaches to the synthesis of high quality face videos may be misused to manipulate videos with malicious intent. The research community therefore developed methods for the detection of modified footage and assembled benchmark datasets for this task. In this paper, we examine how the performance of forgery detectors depends on the presence of artefacts that the human eye can see. We introduce a new benchmark dataset for face video forgery detection, of unprecedented quality. It allows us to demonstrate that existing detection techniques have difficulties detecting fakes that reliably fool the human eye. We thus introduce a new family of detectors that examine combinations of spatial and temporal features and outperform existing approaches both in terms of detection accuracy and generalization., Comment: ICME 2021 camera-ready

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, RigNet is trained between the 3DMM's semantic parameters and StyleGAN's input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face., Comment: CVPR 2020 (Oral). Project page: https://gvv.mpi-inf.mpg.de/projects/StyleRig/

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, including comparisons to state-of-the-art techniques and a user study., Comment: Video: https://youtu.be/s74_yQiJMXA Project/Demo/Code: https://justusthies.github.io/posts/neural-voice-puppetry/

Dubbing is a technique for translating video content from one language to another. However, state-of-the-art visual dubbing techniques directly copy facial expressions from source to target actors without considering identity-specific idiosyncrasies such as a unique type of smile. We present a style-preserving visual dubbing approach from single video inputs, which maintains the signature style of target actors when modifying facial expressions, including mouth motions, to match foreign languages. At the heart of our approach is the concept of motion style, in particular for facial expressions, i.e., the person-specific expression change that is yet another essential factor beyond visual accuracy in face editing applications. Our method is based on a recurrent generative adversarial network that captures the spatiotemporal co-activation of facial expressions, and enables generating and modifying the facial expressions of the target actor while preserving their style. We train our model with unsynchronized source and target videos in an unsupervised manner using cycle-consistency and mouth expression losses, and synthesize photorealistic video frames using a layered neural face renderer. Our approach generates temporally coherent results, and handles dynamic backgrounds. Our results show that our dubbing approach maintains the idiosyncratic style of the target actor better than previous approaches, even for widely differing source and target actors., Comment: SIGGRAPH Asia 2019

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals.We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fully connected neural network turns the possibly partial (on account of occlusion) 2Dpose and 3Dpose features for each subject into a complete 3Dpose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that do not produce joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes., Comment: To appear in ACM Transactions on Graphics (SIGGRAPH) 2020

Face performance capture and reenactment techniques use multiple cameras and sensors, positioned at a distance from the face or mounted on heavy wearable devices. This limits their applications in mobile and outdoor environments. We present EgoFace, a radically new lightweight setup for face performance capture and front-view videorealistic reenactment using a single egocentric RGB camera. Our lightweight setup allows operations in uncontrolled environments, and lends itself to telepresence applications such as video-conferencing from dynamic environments. The input image is projected into a low dimensional latent space of the facial expression parameters. Through careful adversarial training of the parameter-space synthetic rendering, a videorealistic animation is produced. Our problem is challenging as the human visual system is sensitive to the smallest face irregularities that could occur in the final results. This sensitivity is even stronger for video results. Our solution is trained in a pre-processing stage, through a supervised manner without manual annotations. EgoFace captures a wide variety of facial expressions, including mouth movements and asymmetrical expressions. It works under varying illuminations, background, movements, handles people from different ethnicities and can operate in real time., Comment: Project Page: http://gvv.mpi-inf.mpg.de/projects/EgoFace/

Monocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multi-frame consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction., Comment: CVPR 2019 (Oral). Video: https://www.youtube.com/watch?v=SG2BwxCw0lQ, Project Page: https://gvv.mpi-inf.mpg.de/projects/FML19/

In this paper, we study the associations between human faces and voices. Audiovisual integration, specifically the integration of facial and vocal information is a well-researched area in neuroscience. It is shown that the overlapping information between the two modalities plays a significant role in perceptual tasks such as speaker identification. Through an online study on a new dataset we created, we confirm previous findings that people can associate unseen faces with corresponding voices and vice versa with greater than chance accuracy. We computationally model the overlapping information between faces and voices and show that the learned cross-modal representation contains enough information to identify matching faces and voices with performance similar to that of humans. Our representation exhibits correlations to certain demographic attributes and features obtained from either visual or aural modality alone. We release our dataset of audiovisual recordings and demographic annotations of people reading out short text used in our studies., Comment: 27 pages including the supplementary material; Accepted to ACCV 2018

Video motion magnification techniques allow us to see small motions previously invisible to the naked eyes, such as those of vibrating airplane wings, or swaying buildings under the influence of the wind. Because the motion is small, the magnification results are prone to noise or excessive blurring. The state of the art relies on hand-designed filters to extract representations that may not be optimal. In this paper, we seek to learn the filters directly from examples using deep convolutional neural networks. To make training tractable, we carefully design a synthetic dataset that captures small motion well, and use two-frame input for training. We show that the learned filters achieve high-quality results on real videos, with less ringing artifacts and better noise characteristics than previous methods. While our model is not trained with temporal filters, we found that the temporal filters can be used with our extracted representations up to a moderate magnification, enabling a frequency-based motion selection. Finally, we analyze the learned filters and show that they behave similarly to the derivative filters used in previous works. Our code, trained model, and datasets will be available online., Comment: Accepted as ECCV 2018 Oral. The 1st and 2nd authors equally contributed. Video result: https://youtu.be/GrMLeEcSNzY , Project page: http://people.csail.mit.edu/tiam/deepmag/ Some bibliography information was fixed

Single-image-based view generation (SIVG) is important for producing 3D stereoscopic content. Here, handling different spatial resolutions as input and optimizing both reconstruction accuracy and processing speed is desirable. Latest approaches are based on convolutional neural network (CNN), and they generate promising results. However, their use of fully connected layers as well as pre-trained VGG forces a compromise between reconstruction accuracy and processing speed. In addition, this approach is limited to the use of a specific spatial resolution. To remedy these problems, we propose exploiting fully convolutional networks (FCN) for SIVG. We present two FCN architectures for SIVG. The first one is based on combination of an FCN and a view-rendering network called DeepView$_{ren}$. The second one consists of decoupled networks for luminance and chrominance signals, denoted by DeepView$_{dec}$. To train our solutions we present a large dataset of 2M stereoscopic images. Results show that both of our architectures improve accuracy and speed over the state of the art. DeepView$_{ren}$ generates competitive accuracy to the state of the art, however, with the fastest processing speed of all. That is x5 times faster speed and x24 times lower memory consumption compared to the state of the art. DeepView$_{dec}$ has much higher accuracy, but with x2.5 times faster speed and x12 times lower memory consumption. We evaluated our approach with both objective and subjective studies., Comment: 8 pages, 6 figures

Shot boundary detection (SBD) is an important pre-processing step for video manipulation. Here, each segment of frames is classified as either sharp, gradual or no transition. Current SBD techniques analyze hand-crafted features and attempt to optimize both detection accuracy and processing speed. However, the heavy computations of optical flow prevents this. To achieve this aim, we present an SBD technique based on spatio-temporal Convolutional Neural Networks (CNN). Since current datasets are not large enough to train an accurate SBD CNN, we present a new dataset containing more than 3.5 million frames of sharp and gradual transitions. The transitions are generated synthetically using image compositing models. Our dataset contain additional 70,000 frames of important hard-negative no transitions. We perform the largest evaluation to date for one SBD algorithm, on real and synthetic data, containing more than 4.85 million frames. In comparison to the state of the art, we outperform dissolve gradual detection, generate competitive performance for sharp detections and produce significant improvement in wipes. In addition, we are up to 11 times faster than the state of the art.

We present a content-based retrieval method for long surveillance videos both for wide-area (Airborne) as well as near-field imagery (CCTV). Our goal is to retrieve video segments, with a focus on detecting objects moving on routes, that match user-defined events of interest. The sheer size and remote locations where surveillance videos are acquired, necessitates highly compressed representations that are also meaningful for supporting user-defined queries. To address these challenges we archive long-surveillance video through lightweight processing based on low-level local spatio-temporal extraction of motion and object features. These are then hashed into an inverted index using locality-sensitive hashing (LSH). This local approach allows for query flexibility as well as leads to significant gains in compression. Our second task is to extract partial matches to the user-created query and assembles them into full matches using Dynamic Programming (DP). DP exploits causality to assemble the indexed low level features into a video segment which matches the query route. We examine CCTV and Airborne footage, whose low contrast makes motion extraction more difficult. We generate robust motion estimates for Airborne data using a tracklets generation algorithm while we use Horn and Schunck approach to generate motion estimates for CCTV. Our approach handles long routes, low contrasts and occlusion. We derive bounds on the rate of false positives and demonstrate the effectiveness of the approach for counting, motion pattern recognition and abandoned object applications., Comment: 13 pages