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.

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.

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.

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/

Abstract 3D reconstruction of deformable (ornon‐rigid) scenes from a set of monocular 2D image observations is a long‐standing and actively researched area of computer vision and graphics. It is an ill‐posed inverse problem, since—without additional prior assumptions—it permits infinitely many solutions leading to accurate projection to the input 2D images. Non‐rigid reconstruction is a foundational building block for downstream applications like robotics, AR/VR, or visual content creation. The key advantage of using monocular cameras is their omnipresence and availability to the end users as well as their ease of use compared to more sophisticated camera set‐ups such as stereo or multi‐view systems. This survey focuses on state‐of‐the‐art methods for dense non‐rigid 3D reconstruction of various deformable objects and composite scenes from monocular videos or sets of monocular views. It reviews the fundamentals of 3D reconstruction and deformation modeling from 2D image observations. We then start from general methods—that handle arbitrary scenes and make only a few prior assumptions—and proceed towards techniques making stronger assumptions about the observed objects and types of deformations (e.g. human faces, bodies, hands, and animals). A significant part of this STAR is also devoted to classification and a high‐level comparison of the methods, as well as an overview of the datasets for training and evaluation of the discussed techniques. We conclude by discussing open challenges in the field and the social aspects associated with the usage of the reviewed methods.

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.

Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. State-of-the-art 3D generative models are GANs that use neural 3D volumetric representations for synthesis. Images are synthesized by rendering the volumes from a given camera. These models can disentangle the 3D scene from the camera viewpoint in any generated image. However, most models do not disentangle other factors of image formation, such as geometry and appearance. In this paper, we design a 3D GAN which can learn a disentangled model of objects, just from monocular observations. Our model can disentangle the geometry and appearance variations in the scene, i.e., we can independently sample from the geometry and appearance spaces of the generative model. This is achieved using a novel non-rigid deformable scene formulation. A 3D volume that represents an object instance is computed as a non-rigidly deformed canonical 3D volume. Our method learns the canonical volume, as well as its deformations, jointly during training. This formulation also helps us improve the disentanglement between the 3D scene and the camera viewpoints using a novel pose regularization loss defined on the 3D deformation field. In addition, we model the inverse deformations, enabling the computation of dense correspondences between images generated by our model. Finally, we design an approach to embed real images into the latent space of our model, enabling editing of real images.

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.

Differentiable rendering has received increasing interest for image-based inverse problems. It can benefit traditional optimization-based solutions to inverse problems, but also allows for self-supervision of learning-based approaches for which training data with ground truth annotation is hard to obtain. However, existing differentiable renderers either do not model visibility of the light sources from the different points in the scene, responsible for shadows in the images, or are very slow which makes it difficult to train deep architectures over thousands of iterations. To this end, we propose an accurate yet efficient approach for differentiable visibility and soft shadow computation. Our approach is based on the spherical harmonics approximations of the scene illumination and visibility, where the occluding surface is approximated with spheres. This allows for a significantly more efficient shadow computation compared to methods based on ray tracing. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and geometric deformation recovery from images using analysis-by-synthesis optimization.

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.

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.