Accurate three-dimensional (3D) human motion tracking is essential for immersive augmented reality$(A R)$and virtual reality (VR) applications, allowing users to engage with virtual environments through realistic full-body avatars. Achieving this level of detail, however, is challenging when the driving signals are sparse, typically coming only from upper-body sensors, such as head-mounted devices and hand controllers. To address this challenge, we propose EgoMDM (Egocentric Motion Diffusion Model), an end-to-end diffusion-based framework designed to reconstruct full-body motion from sparse tracking signals. EgoMDM models human motion in a conditional autoregressive manner using a unidirectional recurrent neural network, making it well-suited for real-time applications. By embedding local-to-global translation, forward and inverse kinematics, and foot-contact detection within the diffusion framework, EgoMDM achieves seamless, end-to-end motion synthesis, effectively reducing artifacts like foot sliding and ground penetration. Additionally, EgoMDM is conditioned on the user's body scale, allowing it to generalize across a diverse population and produce consistent avatar shapes over time. In our extensive experiments on the AMASS motion capture dataset, EgoMDM achieves state-of-the-art performance in both motion tracking accuracy and synthesis quality, demonstrating its robustness and adaptability across various human motion scenarios. Furthermore, EgoMDM significantly outperforms the existing models when tested on real signal inputs, highlighting its robustness and applicability to the real-world data. See the project page at: https://yohanshin.github.io/egomdm.github.io/

We present Drivable 3D Gaussian Avatars (D3GA), a multi-layered 3D controllable model for human bodies that utilizes 3D Gaussian primitives embedded into tetrahedral cages. The advantage of using cages compared to commonly employed linear blend skinning (LBS) is that primitives like 3D Gaussians are naturally re-oriented and their kernels are stretched via the deformation gradients of the encapsulating tetrahedron. Additional offsets are modeled for the tetrahedron vertices, effectively decoupling the low-dimensional driving poses from the extensive set of primitives to be rendered. This separation is achieved through the localized influence of each tetrahedron on 3D Gaussians, resulting in improved optimization. Using the cage-based deformation model, we introduce a compositional pipeline that decomposes an avatar into layers, such as garments, hands, or faces, improving the modeling of phenomena like garment sliding. These parts can be conditioned on different driving signals, such as keypoints for facial expressions or joint-angle vectors for garments and the body. Our experiments on two multi-view datasets with varied body shapes, clothes, and motions show higher-quality results. They surpass PSNR and SSIM metrics of other SOTA methods using the same data while offering greater flexibility and compactness.

We present Pippo, a generative model capable of producing 1K resolution dense turnaround videos of a person from a single casually clicked photo. Pippo is a multi-view diffusion transformer and does not require any additional inputs — e.g., a fitted parametric model or camera parameters of the input image. We pre-train Pippo on 3B human images without captions, and conduct multi-view mid-training and post-training on studio captured humans. During mid-training, to quickly absorb the studio dataset, we denoise several (upto 48) views at low-resolution, and encode target cameras coarsely using a shallow MLP. During post-training, we denoise fewer views at high-resolution and use pixel-aligned controls (e.g., Spatial anchor and Plucker rays) to enable 3D consistent generations. At inference, we propose an attention biasing technique that allows Pippo to simultaneously generate greater than 5× as many views as seen during training. Finally, we also introduce an improved metric to evaluate 3D consistency of multi-view generations, and show that Pippo outperforms existing works on multi-view human generation from a single image.

We present a framework for generating full-bodied pho-torealistic avatars that gesture according to the conversational dynamics of a dyadic interaction. Given speech au-dio, we output multiple possibilities of gestural motion for an individual, including face, body, and hands. The key be-hind our method is in combining the benefits of sample di-versity from vector quantization with the high-frequency de-tails obtained through diffusion to generate more dynamic, expressive motion. We visualize the generated motion using highly photorealistic avatars that can express crucial nu-ances in gestures (e.g. sneers and smirks). To facilitate this line of research, we introduce a first-of-its-kind multi-view conversational dataset that allows for photorealistic reconstruction. Experiments show our model generates appropri-ate and diverse gestures, outperforming both diffusion- and VQ-only methods. Furthermore, our perceptual evaluation highlights the importance of photorealism (vs. meshes) in accurately assessing subtle motion details in conversational gestures. Code and dataset available on project page.

To build photorealistic avatars that users can embody, human modelling must be complete (cover the full body), driveable (able to reproduce the current motion and appearance from the user), and generalizable (i.e., easily adaptable to novel identities).Towards these goals, paired captures, that is, captures of the same subject obtained from systems of diverse quality and availability, are crucial.However, paired captures are rarely available to researchers outside of dedicated industrial labs: Codec Avatar Studio is our proposal to close this gap.Towards generalization and driveability, we introduce a dataset of 256 subjects captured in two modalities: high resolution multi-view scans of their heads, and video from the internal cameras of a headset.Towards completeness, we introduce a dataset of 4 subjects captured in eight modalities: high quality relightable multi-view captures of heads and hands, full body multi-view captures with minimal and regular clothes, and corresponding head, hands and body phone captures.Together with our data, we also provide code and pre-trained models for different state-of-the-art human generation models.Our datasets and code are available at https://github.com/facebookresearch/ava-256 and https://github.com/facebookresearch/goliath.

While 2D diffusion models generate realistic, high-detail images, 3D shape generation methods like Score Distillation Sampling (SDS) built on these 2D diffusion models produce cartoon-like, over-smoothed shapes. To help explain this discrepancy, we show that the image guidance used in Score Distillation can be understood as the velocity field of a 2D denoising generative process, up to the choice of a noise term. In particular, after a change of variables, SDS resembles a high-variance version of Denoising Diffusion Implicit Models (DDIM) with a differently-sampled noise term: SDS introduces noise i.i.d. randomly at each step, while DDIM infers it from the previous noise predictions. This excessive variance can lead to over-smoothing and unrealistic outputs. We show that a better noise approximation can be recovered by inverting DDIM in each SDS update step. This modification makes SDS's generative process for 2D images almost identical to DDIM. In 3D, it removes over-smoothing, preserves higher-frequency detail, and brings the generation quality closer to that of 2D samplers. Experimentally, our method achieves better or similar 3D generation quality compared to other state-of-the-art Score Distillation methods, all without training additional neural networks or multi-view supervision, and providing useful insights into relationship between 2D and 3D asset generation with diffusion models.

Geometric Deep Learning has recently made striking progress with the advent of continuous deep implicit fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D euclidean grid, resulting in a learnable parameterization that is unlimited in resolution. Unfortunately, these methods are often unsuitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field. In this work, we remove this limitation and introduce a differentiable way to produce explicit surface mesh representations from Deep Implicit Fields. Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field. We exploit this to define DeepMesh - an end-to-end differentiable mesh representation that can vary its topology. We validate our theoretical insight through several applications: Single view 3D Reconstruction via Differentiable Rendering, Physically-Driven Shape Optimization, Full Scene 3D Reconstruction from Scans and End-to-End Training. In all cases our end-to-end differentiable parameterization gives us an edge over state-of-the-art algorithms.

We present the first neural relighting approach for rendering high-fidelity personalized hands that can be animated in real-time under novel illumination. Our approach adopts a teacher-student framework, where the teacher learns appearance under a single point light from images captured in a light-stage, allowing us to synthesize hands in arbitrary illuminations but with heavy compute. Using images rendered by the teacher model as training data, an efficient student model directly predicts appearance under natural illuminations in real-time. To achieve generalization, we condition the student model with physics-inspired illumination features such as visibility, diffuse shading, and specular reflections computed on a coarse proxy geometry, maintaining a small computational overhead. Our key insight is that these features have strong correlation with subsequent global light transport effects, which proves sufficient as conditioning data for the neural relighting network. Moreover, in contrast to bottleneck illumination conditioning, these features are spatially aligned based on underlying geometry, leading to better generalization to unseen illuminations and poses. In our experiments, we demonstrate the efficacy of our illumination feature representations, outperforming baseline approaches. We also show that our approach can photorealistically relight two interacting hands at real-time speeds. https://sh8.io/#/relightable_hands

High-fidelity human 3D models can now be learned directly from videos, typically by combining a template-based surface model with neural representations. However, obtaining a template surface requires expensive multi-view capture systems, laser scans, or strictly controlled conditions. Previous methods avoid using a template but rely on a costly or ill-posed mapping from observation to canonical space. We propose a hybrid point-based representation for reconstructing animatable characters that does not require an explicit surface model, while being generalizable to novel poses. For a given video, our method automatically produces an explicit set of 3D points representing approximate canonical geometry, and learns an articulated deformation model that produces pose-dependent point transformations. The points serve both as a scaffold for high-frequency neural features and an anchor for efficiently mapping between observation and canonical space. We demonstrate on established benchmarks that our representation overcomes limitations of prior work operating in either canonical or in observation space. Moreover, our automatic point extraction approach enables learning models of human and animal characters alike, matching the performance of the methods using rigged surface templates despite being more general. Project website: https://lemonatsu.github.io/npc/.

Clothing is an important part of human appearance but challenging to model in photorealistic avatars. In this work we present avatars with dynamically moving loose clothing that can be faithfully driven by sparse RGB-D inputs as well as body and face motion. We propose a Neural Iterative Closest Point (N-ICP) algorithm that can efficiently track the coarse garment shape given sparse depth input. Given the coarse tracking results, the input RGB-D images are then remapped to texel-aligned features, which are fed into the drivable avatar models to faithfully reconstruct appearance details. We evaluate our method against recent image-driven synthesis baselines, and conduct a comprehensive analysis of the N-ICP algorithm. We demonstrate that our method can generalize to a novel testing environment, while preserving the ability to produce high-fidelity and faithful clothing dynamics and appearance.

We propose a novel multi-view camera pipeline for the reconstruction and registration of dynamic clothing. Our proposed method relies on a specifically designed pattern that allows for precise video tracking in each camera view. We triangulate the tracked points and register the cloth surface in a fine-grained geometric resolution and low localization error. Compared to state-of-the-art methods, our registration exhibits stable correspondence, tracking the same points on the deforming cloth surface along the temporal sequence. As an application, we demonstrate how the use of our registration pipeline greatly improves state-of-the-art pose-based drivable cloth models. Furthermore, we propose a novel model, Garment Avatar , for driving cloth from a dense tracking signal which is obtained from two opposing camera views. The method produces realistic reconstructions which are faithful to the actual geometry of the deforming cloth. In this setting, the user wears a garment with our custom pattern which enables our driving model to reconstruct the geometry. Our code and data are available at https://github.com/HalimiOshri/Pattern-Based-Cloth-Registration-and-Sparse-View-Animation. The released data includes our pattern and registered mesh sequences containing four different subjects and 15k frames in total.

Cameras with a finite aperture diameter exhibit defocus for scene elements that are not at the focus distance, and have only a limited depth of field within which objects appear acceptably sharp. In this work we address the problem of applying inverse rendering techniques to input data that exhibits such defocus blurring. We present differentiable depth-of-field rendering techniques that are applicable to both rasterization-based methods using mesh representations, as well as ray-marching-based methods using either explicit [Yu et al. 2021] or implicit volumetric radiance fields [Mildenhall et al. 2020]. Our approach learns significantly sharper scene reconstructions on data containing blur due to depth of field, and recovers aperture and focus distance parameters that result in plausible forward-rendered images. We show applications to macro photography, where typical lens configurations result in a very narrow depth of field, and to multi-camera video capture, where maintaining sharp focus across a large capture volume for a moving subject is difficult.

Despite recent progress in developing animatable full-body avatars, realistic modeling of clothing - one of the core aspects of human self-expression - remains an open challenge. State-of-the-art physical simulation methods can generate realistically behaving clothing geometry at interactive rates. Modeling photorealistic appearance, however, usually requires physically-based rendering which is too expensive for interactive applications. On the other hand, data-driven deep appearance models are capable of efficiently producing realistic appearance, but struggle at synthesizing geometry of highly dynamic clothing and handling challenging body-clothing configurations. To this end, we introduce pose-driven avatars with explicit modeling of clothing that exhibit both photorealistic appearance learned from real-world data and realistic clothing dynamics. The key idea is to introduce a neural clothing appearance model that operates on top of explicit geometry: at training time we use high-fidelity tracking, whereas at animation time we rely on physically simulated geometry. Our core contribution is a physically-inspired appearance network, capable of generating photorealistic appearance with view-dependent and dynamic shadowing effects even for unseen body-clothing configurations. We conduct a thorough evaluation of our model and demonstrate diverse animation results on several subjects and different types of clothing. Unlike previous work on photorealistic full-body avatars, our approach can produce much richer dynamics and more realistic deformations even for many examples of loose clothing. We also demonstrate that our formulation naturally allows clothing to be used with avatars of different people while staying fully animatable, thus enabling, for the first time, photorealistic avatars with novel clothing.

Deep neural networks have amply demonstrated their prowess but estimating the reliability of their predictions remains challenging. Deep Ensembles are widely considered as being one of the best methods for generating uncertainty estimates but are very expensive to train and evaluate.MC-Dropout is another popular alternative, which is less expensive, but also less reliable. Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples. The first one uses effectively infinite number of highly correlated models while the second one relies on a finite number of independent models.To combine the benefits of both, we introduce Masksembles. Instead of randomly dropping parts of the network as in MC-dropout, Masksemble relies on a fixed number of binary masks, which are parameterized in a way that allows to change correlations between individual models. Namely, by controlling the overlap between the masks and their size one can choose the optimal configuration for the task at hand. This leads to a simple and easy to implement method with performance on par with Ensembles at a fraction of the cost. We experimentally validate Masksembles on two widely used datasets, CIFAR10 and ImageNet.

Photorealistic rendering of dynamic humans is an important capability for telepresence systems, virtual shopping, special effects in movies, and interactive experiences such as games. Recently, neural rendering methods have been developed to create high-fidelity models of humans and objects. Some of these methods do not produce results with high-enough fidelity for driveable human models (Neural Volumes) whereas others have extremely long rendering times (NeRF). We propose a novel compositional 3D representation that combines the best of previous methods to produce both higher-resolution and faster results. Our representation bridges the gap between discrete and continuous volumetric representations by combining a coarse 3D-structure-aware grid of animation codes with a continuous learned scene function that maps every position and its corresponding local animation code to a view-dependent emitted radiance and local volume density. Differentiable volume rendering is employed to compute photo-realistic novel views of the human head and upper body as well as to train our novel representation end-to-end using only 2D supervision. In addition, we show that the learned dynamic radiance field can be used to synthesize novel unseen expressions based on a global animation code. Our approach achieves state-of-the-art results for synthesizing novel views of dynamic human heads and the upper body. See our project page1for more results.

We present a learning-based method for building driving-signal aware full-body avatars. Our model is a conditional variational autoencoder that can be animated with incomplete driving signals, such as human pose and facial keypoints, and produces a high-quality representation of human geometry and view-dependent appearance. The core intuition behind our method is that better drivability and generalization can be achieved by disentangling the driving signals and remaining generative factors, which are not available during animation. To this end, we explicitly account for information deficiency in the driving signal by introducing a latent space that exclusively captures the remaining information, thus enabling the imputation of the missing factors required during full-body animation, while remaining faithful to the driving signal. We also propose a learnable localized compression for the driving signal which promotes better generalization, and helps minimize the influence of global chance-correlations often found in real datasets. For a given driving signal, the resulting variational model produces a compact space of uncertainty for missing factors that allows for an imputation strategy best suited to a particular application. We demonstrate the efficacy of our approach on the challenging problem of full-body animation for virtual telepresence with driving signals acquired from minimal sensors placed in the environment and mounted on a VR-headset.

We have recently seen great progress in building photorealistic animatable full-body codec avatars, but generating high-fidelity animation of clothing is still difficult. To address these difficulties, we propose a method to build an animatable clothed body avatar with an explicit representation of the clothing on the upper body from multi-view captured videos. We use a two-layer mesh representation to register each 3D scan separately with the body and clothing templates. In order to improve the photometric correspondence across different frames, texture alignment is then performed through inverse rendering of the clothing geometry and texture predicted by a variational autoencoder. We then train a new two-layer codec avatar with separate modeling of the upper clothing and the inner body layer. To learn the interaction between the body dynamics and clothing states, we use a temporal convolution network to predict the clothing latent code based on a sequence of input skeletal poses. We show photorealistic animation output for three different actors, and demonstrate the advantage of our clothed-body avatars over the single-layer avatars used in previous work. We also show the benefit of an explicit clothing model that allows the clothing texture to be edited in the animation output.

Geometric Deep Learning has recently made striking progress with the advent of continuous Deep Implicit Fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid, resulting in a learnable parameterization that is not limited in resolution. Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying implicit field. In this work, we remove this limitation and introduce a differentiable way to produce explicit surface mesh representations from Deep Signed Distance Functions. Our key insight is that by reasoning on how implicit field perturbations impact local surface geometry, one can ultimately differentiate the 3D location of surface samples with respect to the underlying deep implicit field. We exploit this to define MeshSDF, an end-to-end differentiable mesh representation which can vary its topology. We use two different applications to validate our theoretical insight: Single-View Reconstruction via Differentiable Rendering and Physically-Driven Shape Optimization. In both cases our differentiable parameterization gives us an edge over state-of-the-art algorithms.

We propose a method for learning non-linear face geometry representations using deep generative models. Our model is a variational autoencoder with multiple levels of hidden variables where lower layers capture global geometry and higher ones encode more local deformations. Based on that, we propose a new parameterization of facial geometry that naturally decomposes the structure of the human face into a set of semantically meaningful levels of detail. This parameterization enables us to do model fitting while capturing varying level of detail under different types of geometrical constraints.

People detection methods are highly sensitive to occlusions between pedestrians, which are extremely frequent in many situations where cameras have to be mounted at a limited height. The reduction of camera prices allows for the generalization of static multi-camera set-ups. Using joint visual information from multiple synchronized cameras gives the opportunity to improve detection performance. In this paper, we present a new large-scale and high-resolution dataset. It has been captured with seven static cameras in a public open area, and unscripted dense groups of pedestrians standing and walking. Together with the camera frames, we provide an accurate joint (extrinsic and intrinsic) calibration, as well as 7 series of 400 annotated frames for detection at a rate of 2 frames per second. This results in over 40 000 bounding boxes delimiting every person present in the area of interest, for a total of more than 300 individuals. We provide a series of benchmark results using baseline algorithms published over the recent months for multi-view detection with deep neural networks, and trajectory estimation using a non-Markovian model.

We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end to generate dense proposal maps that are refined via a novel inference scheme. The temporal consistency is handled via a person-level matching Recurrent Neural Network. The complete model takes as input a sequence of frames and outputs detections along with the estimates of individual actions and collective activities. We demonstrate state-of-the-art performance of our algorithm on multiple publicly available benchmarks.

Mean-field variational inference is one of the most popular approaches to inference in discrete random fields. Standard mean-field optimization is based on coordinate descent and in many situations can be impractical. Thus, in practice, various parallel techniques are used, which either rely on ad hoc smoothing with heuristically set parameters, or put strong constraints on the type of models. In this paper, we propose a novel proximal gradient-based approach to optimizing the variational objective. It is naturally parallelizable and easy to implement. We prove its convergence, and demonstrate that, in practice, it yields faster convergence and often finds better optima than more traditional mean-field optimization techniques. Moreover, our method is less sensitive to the choice of parameters.

We propose a novel approach to computing the probabilities of presence of multiple and potentially occluding objects in a scene from a single depth map. To this end, we use a generative model that predicts the distribution of depth images that would be produced if the probabilities of presence were known and then to optimize them so that this distribution explains observed evidence as closely as possible. This allows us to exploit very effectively the available evidence and outperform state-of-the-art methods without requiring large amounts of data, or without using the RGB signal that modern RGB-D sensors also provide.

Progressive algorithms are algorithms that, on the way to computing a complete solution to the problem at hand, output intermediate solutions that approximate the complete solution increasingly well. We present a framework for analyzing such algorithms, and develop efficient progressive algorithms for two geometric problems: computing the convex hull of a planar point set, and finding popular places in a set of trajectories.