Event cameras offer a considerable alternative to RGB cameras in many scenarios. While there are recent works on event-based novel-view synthesis, dense 3D mesh reconstruction remains scarcely explored and existing event-based techniques are severely limited in their 3D reconstruction accuracy. To address this limitation, we present EventNeuS, a self-supervised neural model for learning 3D representations from monocular colour event streams. Our approach, for the first time, combines 3D signed distance function and density field learning with event-based supervision. Furthermore, we introduce spherical harmonics encodings into our model for enhanced handling of view-dependent effects. EventNeuS outperforms existing approaches by a significant margin, achieving 34% lower Chamfer distance and 31% lower mean absolute error on average compared to the best previous method.

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 volumetric 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 in the 3D volume. The training of such a generator with a high degree of freedom is made possible through a combination of adversarial and knowledge distillation training. The learned model exhibits dense 3D correspondences between samples. We provide exhaustive qualitative and qualitative evaluations for dense correspondences. Experiments on several datasets demonstrate superior efficiency, 3D consistency, and the emergence of dense correspondences of GVP over the state-of-the-art.

Rendering novel, relit views of a human head, given a monocular portrait image as input, is an inherently underconstrained problem. The traditional graphics solution is to explicitly decompose the input image into geometry, material and lighting via differentiable rendering; but this is constrained by the multiple assumptions and approximations of the underlying models and parameterizations of these scene components. We propose 3DPR, an image-based relighting model that leverages generative priors learnt from multi-view One-Light-at-A-Time (OLAT) images captured in a light stage. We introduce a new diverse and large-scale multi-view 4K OLAT dataset of 139 subjects to learn a high-quality prior over the distribution of high-frequency face reflectance. We leverage the latent space of a pre-trained generative head model that provides a rich prior over face geometry learnt from in-the-wild image datasets. The input portrait is first embedded in the latent manifold of such a model through an encoder-based inversion process. Then a novel triplane-based reflectance network trained on our lightstage data is used to synthesize high-fidelity OLAT images to enable image-based relighting. Our reflectance network operates in the latent space of the generative head model, crucially enabling a relatively small number of lightstage images to train the reflectance model. Combining the generated OLATs according to a given HDRI environment maps yields physically accurate environmental relighting results. Through quantitative and qualitative evaluations, we demonstrate that 3DPR outperforms previous methods, particularly in preserving identity and in capturing lighting effects such as specularities, self-shadows, and subsurface scattering.

Event cameras report events whenever an individual pixel changes brightness. The discrete and asynchronous nature of events makes recovering pixel brightness signals a challenging task, even if conventional brightness frames are recorded along with events. Recent works have addressed this task with neural networks, which tend to be biased towards their training distribution. All methods need to deal with noise in the events to produce very high output framerates. We introduce a new approach to event-based reconstruction, not learning-based: Our model assigns each event an explicit confidence weight to account for the uncertainty arising from noise. We also introduce a novel loss term to balance confidences against each other and show that interpolation of brightness signals between events can benefit from Bézier curves. We demonstrate that allowing brightness changes between exposures can improve reconstruction quality. Our evaluation shows that our method improves the state of the art in the tasks of event-based de-blurring and event-based frame interpolation.

Abstract Portrait viewpoint and illumination editing is an important problem with several applications in VR/AR, movies, and photography. Comprehensive knowledge of geometry and illumination is critical for obtaining photorealistic results. Current methods are unable to explicitly model in 3D while handling both viewpoint and illumination editing from a single image. In this paper, we propose VoRF, a novel approach that can take even a single portrait image as input and relight human heads under novel illuminations that can be viewed from arbitrary viewpoints. VoRF represents a human head as a continuous volumetric field and learns a prior model of human heads using a coordinate-based MLP with individual latent spaces for identity and illumination. The prior model is learned in an auto-decoder manner over a diverse class of head shapes and appearances, allowing VoRF to generalize to novel test identities from a single input image. Additionally, VoRF has a reflectance MLP that uses the intermediate features of the prior model for rendering One-Light-at-A-Time (OLAT) images under novel views. We synthesize novel illuminations by combining these OLAT images with target environment maps. Qualitative and quantitative evaluations demonstrate the effectiveness of VoRF for relighting and novel view synthesis, even when applied to unseen subjects under uncontrolled illumination. This work is an extension of Rao et al. (VoRF: Volumetric Relightable Faces 2022). We provide extensive evaluation and ablative studies of our model and also provide an application, where any face can be relighted using textual input.

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, they often fail 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 can 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 learnable parameters 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. We make the code available on our project page.

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 article 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 a resolution of 480 x 270. Our method outperforms related approaches both visually and numerically. We will release our multiple-identity dataset to encourage further research.

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.

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/

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 the remaining time steps via a pre-trained 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.

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 learnt 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 rest of the object fixed. We evaluate our method on a wide variety of objects and parts, and demonstrate editing applications.

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/.

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. The code will be available at https://github.com/cong-yi/DMM

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 such as higher-order global illumination effects and self-shadowing. 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 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 dataset, which captures 300 people illuminated with 150 light conditions from 8 viewpoints. We show that our method outperforms existing monocular reflectance reconstruction methods due to better capturing of physical effects, such as sub-surface scattering, specularities, self-shadows and other higher-order effects.

Most 3D face reconstruction methods rely on 3D morphable models, which disentangle the space of facial deformations into identity and expression geometry, 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 and expression geometry, and reflectance, 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. We show that the learned model can also be personalized to a video, for a better capture of the geometry and albedo.

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. The source code is available at https://graphics.tu-bs.de/publications/kappel2020high-fidelity.

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 available1.

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/).

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.

We propose the first approach to synthesize 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 corpus that contains more than 33 hours of annotated 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 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.

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 proposed method removes complex reflections in videos by including the user in the loop. The method is flexible and can accept various levels of user annotations, within each frame and in the number of frames being annotated. The user provides some strokes in some of the frames in the video, and our method propagates these strokes within the frame using a random walk computation as well as across frames using a point-based motion tracking method. 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.

Photorealistic editing of head 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 (parameterised with an environment map) 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.

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, 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.

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.

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 fullyconnected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose 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.

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.

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.

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.

In this work, we propose two ensemble methods leveraging a crowd workforce to improve video annotation, with a focus on video object segmentation. Their shared principle is that while individual candidate results may likely be insufficient, they often complement each other so that they can be combined into something better than any of the individual results---the very spirit of collaborative working. For one, we extend a standard polygon-drawing interface to allow workers to annotate negative space, and combine the work of multiple workers instead of relying on a single best one as commonly done in crowdsourced image segmentation. For the other, we present a method to combine multiple automatic propagation algorithms with the help of the crowd. Such combination requires an understanding of where the algorithms fail, which we gather using a novel coarse scribble video annotation task. We evaluate our ensemble methods, discuss our design choices for them, and make our web-based crowdsourcing tools and results publicly available.

A wide adoption of 3-D videos is hindered by the lack of high-quality 3-D content. One promising solution to this problem is through data-driven 2-D-to-3-D video conversion. Such approaches are based on learning depth maps from a large dataset of 2-D+Depth images. However, current conversion methods, while general, produce low-quality results with artifacts that are not acceptable to many viewers. We propose a novel, data-driven method for 2-D-to-3-D video conversion. Our method transfers the depth gradients from a large database of 2-D+Depth images. Capturing 2-D+Depth databases, however, are complex and costly, especially for outdoor sports games. We address this problem by creating a synthetic database from computer games and showing that this synthetic database can effectively be used to convert real videos. We propose a spatio-temporal method to ensure the smoothness of the generated depth within individual frames and across successive frames. In addition, we present an object boundary detection method customized for 2-D-to-3-D conversion systems, which produces clear depth boundaries for players. We implement our method and validate it by conducting user studies that evaluate depth perception and visual comfort of the converted 3-D videos. We show that our method produces high-quality 3-D videos that are almost indistinguishable from videos shot by stereo cameras. In addition, our method significantly outperforms the current state-of-the-art methods. For example, up to 20% improvement in the perceived depth is achieved by our method, which translates to improving the mean opinion score from good to excellent.

Reflections can obstruct content during video capture and hence their removal is desirable. Current removal techniques are designed for still images, extracting only one reflection (foreground) and one background layer from the input. When extended to videos, unpleasant artifacts such as temporal flickering and incomplete separation are generated. We present a technique for video reflection removal by jointly solving for motion and separation. The novelty of our work is in our optimization formulation as well as the motion initialization strategy. We present a novel spatiotemporal optimization that takes n frames as input and directly estimates 2n frames as output, n for each layer. We aim to fully utilize spatio-temporal information in our objective terms. Our motion initialization is based on iterative frame-to-frame alignment instead of the direct alignment used by current approaches. We compare against advanced video extensions of the state of the art, and we significantly reduce temporal flickering and improve separation. In addition, we reduce image blur and recover moving objects more accurately. We validate our approach through subjective and objective evaluations on real and controlled data.

With the recent availability of commodity Virtual Reality (VR) products, immersive video content is receiving a significant interest. However, producing high-quality VR content often requires upgrading the entire production pipeline, which is costly and time-consuming. In this work, we propose using video feeds from regular broadcasting cameras to generate immersive content. We utilize the motion of the main camera to generate a wide-angle panorama. Using various techniques, we remove the parallax and align all video feeds. We then overlay parts from each video feed on the main panorama using Poisson blending. We examined our technique on various sports including basketball, ice hockey and volleyball. Subjective studies show that most participants rated their immersive experience when viewing our generated content between Good to Excellent. In addition, most participants rated their sense of presence to be similar to ground-truth content captured using a GoPro Omni 360 camera rig.

We present a content-based retrieval method for long-surveillance videos in wide-area (airborne) and near-field [closed-circuit television (CCTV)] imagery. 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 spatiotemporal extraction of motion and object 2. These are then hashed into an inverted index using locality-sensitive hashing. This local approach allows for query flexibility and leads to significant gains in compression. Our second task is to extract partial matches to user-created queries and assemble them into full matches using dynamic programming (DP). DP assembles the indexed low-level features into a video segment that matches the query route by exploiting causality. 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 the 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.

Head portraits are popular in traditional painting. Automating portrait painting is challenging as the human visual system is sensitive to the slightest irregularities in human faces. Applying generic painting techniques often deforms facial structures. On the other hand portrait painting techniques are mainly designed for the graphite style and/or are based on image analogies; an example painting as well as its original unpainted version are required. This limits their domain of applicability. We present a new technique for transferring the painting from a head portrait onto another. Unlike previous work our technique only requires the example painting and is not restricted to a specific style. We impose novel spatial constraints by locally transferring the color distributions of the example painting. This better captures the painting texture and maintains the integrity of facial structures. We generate a solution through Convolutional Neural Networks and we present an extension to video. Here motion is exploited in a way to reduce temporal inconsistencies and the shower-door effect. Our approach transfers the painting style while maintaining the input photograph identity. In addition it significantly reduces facial deformations over state of the art.

Video magnification reveals subtle variations that would be otherwise invisible to the naked eye. Current techniques require all motion in the video to be very small, which is unfortunately not always the case. Tiny yet meaningful motions are often combined with larger motions, such as the small vibrations of a gate as it rotates, or the microsaccades in a moving eye. We present a layer-based video magnification approach that can amplify small motions within large ones. An examined region/layer is temporally aligned and subtle variations are magnified. Matting is used to magnify only region of interest while maintaining integrity of nearby sites. Results show handling larger motions, larger amplification factors and significant reduction in artifacts over state of the art.

A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artifacts that are not acceptable to many viewers. We address this problem by showing how to construct a high-quality, domain-specific conversion method for soccer videos. We propose a novel, data-driven method that generates stereoscopic frames by transferring depth information from similar frames in a database of 3D stereoscopic videos. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. One of the key findings in this paper is showing that computer generated content in current sports computer games can be used to generate high-quality 3D video reference database for 2D-to-3D conversion methods. Once we retrieve similar 3D video frames, our technique transfers depth gradients to the target frame while respecting object boundaries. It then computes depth maps from the gradients, and generates the output stereoscopic video. We implement our method and validate it by conducting user-studies that evaluate depth perception and visual comfort of the converted 3D videos. We show that our method produces high-quality 3D videos that are almost indistinguishable from videos shot by stereo cameras. In addition, our method significantly outperforms the current state-of-the-art method. For example, up to 20% improvement in the perceived depth is achieved by our method, which translates to improving the mean opinion score from Good to Excellent.

Reflections in image sequences consist of several layers superimposed over each other. This phenomenon causes many image processing techniques to fail as they assume the presence of only one layer at each examined site e.g. motion estimation and object recognition. This work presents an automated technique for detecting reflections in image sequences by analyzing motion trajectories of feature points. It models reflection as regions containing two different layers moving over each other. We present a strong detector based on combining a set of weak detectors. We use novel priors, generate sparse and dense detection maps and our results show high detection rate with rejection to pathological motion and occlusion.

Automated blotch removal is important in film restoration and typically involves a detection/interpolation step. Current algorithms model the corruption as a binary mixture between the original, clean images and an opaque (dirt) field. This typically causes incomplete blotch removal that manifests as blotch haloes in reconstruction. This paper proposes a new approach by modeling the corruption as a continuous mixture between the two components and generating a solution using a Bayesian framework. We use novel priors, propose a computationally efficient scheme for implementation and our results show more complete blotch reconstruction.