3D head avatars built with neural implicit volumetric representations have achieved unprecedented levels of pho-torealism. However, the computational cost of these methods remains a significant barrier to their widespread adoption, particularly in real-time applications such as virtual reality and teleconferencing. While attempts have been made to develop fast neural rendering approaches for static scenes, these methods cannot be simply employed to support realistic facial expressions, such as in the case of a dynamic facial performance. To address these challenges, we propose a novel fast 3D neural implicit head avatar model that achieves real-time rendering while maintaining fine-grained controllability and high rendering quality. Our key idea lies in the introduction of local hash table blendshapes, which are learned and attached to the vertices of an underlying face parametric model. These per-vertex hash-tables are linearly merged with weights predicted via a CNN, re-sulting in expression dependent embeddings. Our novel representation enables efficient density and color predictions using a lightweight MLP, which is further accelerated by a hierarchical nearest neighbor search method. Extensive experiments show that our approach runs in real-time while achieving comparable rendering quality to state-of-the-arts and decent results on challenging expressions.

We propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild. The learnt avatar is driven by a parametric face model to achieve user-controlled facial expressions and head poses. Our hybrid pipeline combines the geometry prior and dynamic tracking of a 3DMM with a neural radiance field to achieve fine-grained control and photorealism. To reduce over-smoothing and improve out-of-model expressions synthesis, we propose to predict local features anchored on the 3DMM geometry. These learnt features are driven by 3DMM deformation and interpolated in 3D space to yield the volumetric radiance at a designated query point. We further show that using a Convolutional Neural Network in the UV space is critical in incorporating spatial context and producing representative local features. Extensive experiments show that we are able to reconstruct high-quality avatars, with more accurate expression-dependent details, good generalization to out-of-training expressions, and quantitatively superior renderings compared to other state-of-the-art approaches.

We propose a novel transformer-based framework that reconstructs two high fidelity hands from multi-view RGB images. Unlike existing hand pose estimation methods, where one typically trains a deep network to regress hand model parameters from single RGB image, we consider a more challenging problem setting where we directly regress the absolute root poses of two-hands with extended forearm at high resolution from egocentric view. As existing datasets are either infeasible for egocentric viewpoints or lack background variations, we create a large-scale synthetic dataset with diverse scenarios and collect a real dataset from multi-calibrated camera setup to verify our proposed multi-view image feature fusion strategy. To make the reconstruction physically plausible, we propose two strategies: (i) a coarse-to-fine spectral graph convolution decoder to smoothen the meshes during upsampling and (ii) an optimisation-based refinement stage at inference to prevent self-penetrations. Through extensive quantitative and qualitative evaluations, we show that our framework is able to produce realistic two-hand reconstructions and demonstrate the generalisation of synthetic-trained models to real data, as well as real-time AR/VR applications.

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle large motion or visually ambiguous body parts, e.g., left vs. right hand. In contrast, we propose a deep learning framework that maps each pixel to a feature space, where the feature distances reflect the geodesic distances among pixels as if they were projected onto the surface of a 3D human scan. To this end, we introduce novel loss functions to push features apart according to their geodesic distances on the surface. Without any semantic annotation, the proposed embeddings automatically learn to differentiate visually similar parts and align different subjects into an unified feature space. Extensive experiments show that the learned embeddings can produce accurate correspondences between images with remarkable generalization capabilities on both intra and inter subjects.1

We describe a novel approach for compressing truncated signed distance fields (TSDF) stored in 3D voxel grids, and their corresponding textures. To compress the TSDF, our method relies on a block-based neural network architecture trained end-to-end, achieving state-of-the-art rate-distortion trade-off. To prevent topological errors, we losslessly com- press the signs of the TSDF, which also upper bounds the reconstruction error by the voxel size. To compress the corresponding texture, we designed a fast block-based UV parameterization, generating coherent texture maps that can be effectively compressed using existing video compression algorithms. We demonstrate the performance of our algo- rithms on two 4D performance capture datasets, reducing bitrate by 66% for the same distortion, or alternatively re- ducing the distortion by 50% for the same bitrate, compared to the state-of-the-art.

We present "The Relightables", a volumetric capture system for photorealistic and high quality relightable full-body performance capture. While significant progress has been made on volumetric capture systems, focusing on 3D geometric reconstruction with high resolution textures, much less work has been done to recover photometric properties needed for relighting. Results from such systems lack high-frequency details and the subject's shading is prebaked into the texture. In contrast, a large body of work has addressed relightable acquisition for image-based approaches, which photograph the subject under a set of basis lighting conditions and recombine the images to show the subject as they would appear in a target lighting environment. However, to date, these approaches have not been adapted for use in the context of a high-resolution volumetric capture system. Our method combines this ability to realistically relight humans for arbitrary environments, with the benefits of free-viewpoint volumetric capture and new levels of geometric accuracy for dynamic performances. Our subjects are recorded inside a custom geodesic sphere outfitted with 331 custom color LED lights, an array of high-resolution cameras, and a set of custom high-resolution depth sensors. Our system innovates in multiple areas: First, we designed a novel active depth sensor to capture 12.4 MP depth maps, which we describe in detail. Second, we show how to design a hybrid geometric and machine learning reconstruction pipeline to process the high resolution input and output a volumetric video. Third, we generate temporally consistent reflectance maps for dynamic performers by leveraging the information contained in two alternating color gradient illumination images acquired at 60Hz. Multiple experiments, comparisons, and applications show that The Relightables significantly improves upon the level of realism in placing volumetrically captured human performances into arbitrary CG scenes.

Real time non-rigid reconstruction pipelines are extremely computationally expensive and easily saturate the highest end GPUs currently available. This requires careful strategic choices to be made about a set of highly interconnected parameters that divide up the limited compute. At the same time, offline systems, prove the value of increasing voxel resolution, more iterations, and higher frame rates. To this end, we demonstrate a set of remarkably simple but effective modifications to these algorithms that significantly reduce the average per-frame computation cost allowing these parameters to be increased. Specifically, we divide the depth stream into sub-frames and fusion-frames, disabling both model accumulation (fusion) and non-rigid alignment (model tracking) on the former. Instead, we efficiently track point correspondences across neighboring sub-frames. We then leverage these correspondences to initialize the standard non-rigid alignment to a fusion-frame where data can then be accumulated into the model. As a result, compute resources in the modified non-rigid reconstruction pipeline can be immediately re-purposed to increase voxel resolution, use more iterations or to increase the frame rate. To demonstrate the latter, we leverage recent high frame rate depth algorithms to build a novel “twin” sensor consisting of a low-res/highfps sub-frame camera and a second low-fps/high-res fusion camera.

The advent of consumer depth cameras has incited the development of a new cohort of algorithms tackling challenging computer vision problems. The primary reason is that depth provides direct geometric information that is largely invariant to texture and illumination. As such, substantial progress has been made in human and object pose estimation, 3D reconstruction and simultaneous localization and mapping. Most of these algorithms naturally benefit from the ability to accurately track the pose of an object or scene of interest from one frame to the next. However, commercially available depth sensors (typically running at 30fps) can allow for large inter-frame motions to occur that make such tracking problematic. A high frame rate depth camera would thus greatly ameliorate these issues, and further increase the tractability of these computer vision problems. Nonetheless, the depth accuracy of recent systems for high-speed depth estimation [Fanello et al. 2017b] can degrade at high frame rates. This is because the active illumination employed produces a low SNR and thus a high exposure time is required to obtain a dense accurate depth image. Furthermore in the presence of rapid motion, longer exposure times produce artifacts due to motion blur, and necessitates a lower frame rate that introduces large inter-frame motion that often yield tracking failures. In contrast, this paper proposes a novel combination of hardware and software components that avoids the need to compromise between a dense accurate depth map and a high frame rate. We document the creation of a full 3D capture system for high speed and quality depth estimation, and demonstrate its advantages in a variety of tracking and reconstruction tasks. We extend the state of the art active stereo algorithm presented in Fanello et al. [2017b] by adding a space-time feature in the matching phase. We also propose a machine learning based depth refinement step that is an order of magnitude faster than traditional postprocessing methods. We quantitatively and qualitatively demonstrate the benefits of the proposed algorithms in the acquisition of geometry in motion. Our pipeline executes in 1.1ms leveraging modern GPUs and off-the-shelf cameras and illumination components. We show how the sensor can be employed in many different applications, from [non-]rigid reconstructions to hand/face tracking. Further, we show many advantages over existing state of the art depth camera technologies beyond framerate, including latency, motion artifacts, multi-path errors, and multi-sensor interference.

We introduce a realtime compression architecture for 4D performance capture that is two orders of magnitude faster than current state-of-the-art techniques, yet achieves comparable visual quality and bitrate. We note how much of the algorithmic complexity in traditional 4D compression arises from the necessity to encode geometry using an explicit model (i.e. a triangle mesh). In contrast, we propose an encoder that leverages an implicit representation (namely a Signed Distance Function) to represent the observed geometry, as well as its changes through time. We demonstrate how SDFs, when defined over a small local region (i.e. a block), admit a low-dimensional embedding due to the innate geometric redundancies in their representation. We then propose an optimization that takes a Truncated SDF (i.e. a TSDF), such as those found in most rigid/non-rigid reconstruction pipelines, and efficiently projects each TSDF block onto the SDF latent space. This results in a collection of low entropy tuples that can be effectively quantized and symbolically encoded. On the decoder side, to avoid the typical artifacts of block-based coding, we also propose a variational optimization that compensates for quantization residuals in order to penalize unsightly discontinuities in the decompressed signal. This optimization is expressed in the SDF latent embedding, and hence can also be performed efficiently. We demonstrate our compression/decompression architecture by realizing, to the best of our knowledge, the first system for streaming a real-time captured 4D performance on consumer-level networks.

We present Motion2Fusion, a state-of-the-art 360 performance capture system that enables *real-time* reconstruction of arbitrary non-rigid scenes. We provide three major contributions over prior work: 1) a new non-rigid fusion pipeline allowing for far more faithful reconstruction of high frequency geometric details, avoiding the over-smoothing and visual artifacts observed previously. 2) a high speed pipeline coupled with a machine learning technique for 3D correspondence field estimation reducing tracking errors and artifacts that are attributed to fast motions. 3) a backward and forward non-rigid alignment strategy that more robustly deals with topology changes but is still free from scene priors. Our novel performance capture system demonstrates real-time results nearing 3x speed-up from previous state-of-the-art work on the exact same GPU hardware. Extensive quantitative and qualitative comparisons show more precise geometric and texturing results with less artifacts due to fast motions or topology changes than prior art.

We present an end-to-end system for augmented and virtual reality telepresence, called Holoportation. Our system demonstrates high-quality, real-time 3D reconstructions of an entire space, including people, furniture and objects, using a set of new depth cameras. These 3D models can also be transmitted in real-time to remote users. This allows users wearing virtual or augmented reality displays to see, hear and interact with remote participants in 3D, almost as if they were present in the same physical space. From an audio-visual perspective, communicating and interacting with remote users edges closer to face-to-face communication. This paper describes the Holoportation technical system in full, its key interactive capabilities, the application scenarios it enables, and an initial qualitative study of using this new communication medium.

We contribute a new pipeline for live multi-view performance capture, generating temporally coherent high-quality reconstructions in real-time. Our algorithm supports both incremental reconstruction, improving the surface estimation over time, as well as parameterizing the nonrigid scene motion. Our approach is highly robust to both large frame-to-frame motion and topology changes, allowing us to reconstruct extremely challenging scenes. We demonstrate advantages over related real-time techniques that either deform an online generated template or continually fuse depth data nonrigidly into a single reference model. Finally, we show geometric reconstruction results on par with offline methods which require orders of magnitude more processing time and many more RGBD cameras.

We present a 3D scanning system for deformable objects that uses only a single Kinect sensor. Our work allows considerable amount of nonrigid deformations during scanning, and achieves high quality results without heavily constraining user or camera motion. We do not rely on any prior shape knowledge, enabling general object scanning with freeform deformations. To deal with the drift problem when nonrigidly aligning the input sequence, we automatically detect loop closures, distribute the alignment error over the loop, and finally use a bundle adjustment algorithm to optimize for the latent 3D shape and nonrigid deformation parameters simultaneously. We demonstrate high quality scanning results in some challenging sequences, comparing with state of art nonrigid techniques, as well as ground truth data.

In this paper, we introduce a system to capture the enhanced 3D structure of a room-sized dynamic scene with commodity depth cameras such as Microsoft Kinects. It is challenging to capture the entire dynamic room. First, the raw data from depth cameras are noisy due to the conflicts of the room's large volume and cameras' limited optimal working distance. Second, the severe occlusions between objects lead to dramatic missing data in the captured 3D. Our system incorporates temporal information to achieve a noise-free and complete 3D capture of the entire room. More specifically, we pre-scan the static parts of the room offline, and track their movements online. For the dynamic objects, we perform non-rigid alignment between frames and accumulate data over time. Our system also supports the topology changes of the objects and their interactions. We demonstrate the success of our system with various situations.

The 3D data collected using state-of-the-art algorithms often suffers from various problems, such as incompletion and inaccuracy. Using temporal information has been proven effective for improving the reconstruction quality; for example, KinectFusion [21] shows significant improvements for static scenes. In this work, we present a system that uses commodity depth and color cameras, such as Microsoft Kinects, to fuse the 3D data captured over time for dynamic objects to build a complete and accurate model, and then tracks the model to match later observations. The key ingredients of our system include a nonrigid matching algorithm that aligns 3D observations of dynamic objects by using both geometry and texture measurements, and a volumetric fusion algorithm that fuses noisy 3D data. We demonstrate that the quality of the model improves dramatically by fusing a sequence of noisy and incomplete depth data of human and that by deforming this fused model to later observations, noise-and-hole-free 3D models are generated for the human moving freely.

In this paper we propose a general-purpose telepresence system design that can be adapted to a wide range of scenarios and present a framework for a proof-of-concept prototype. The prototype system allows users to see remote participants and their surroundings merged into the local environment through the use of an optical see-through head-worn display. Real-time 3D acquisition and head tracking allows the remote imagery to be seen from the correct point of view and with proper occlusion. A projector-based lighting control system permits the remote imagery to appear bright and opaque even in a lit room. Immersion can be adjusted across the VR continuum. Our approach relies only on commodity hardware; we also experiment with wider field of view custom displays.

We present a room-sized telepresence system for informal gatherings rather than conventional meetings. Unlike conventional systems which constrain participants to sit in fixed positions, our system aims to facilitate casual conversations between people in two sites. The system consists of a wall of large flat displays at each of the two sites, showing a panorama of the remote scene, constructed from a multiplicity of color and depth cameras. The main contribution of this paper is a solution that ameliorates the eye contact problem during conversation in typical scenarios while still maintaining a consistent view of the entire room for all participants. We achieve this by using two sets of cameras - a cluster of ”Panorama Cameras” located at the center of the display wall and are used to capture a panoramic view of the entire room, and a set of ”Personal Cameras” distributed along the display wall to capture front views of nearby participants. A robust segmentation algorithm with the assistance of depth cameras and an image synthesis algorithm work together to generate a consistent view of the entire scene. In our experience this new approach generates fewer distracting artifacts than conventional 3D reconstruction methods, while effectively correcting for eye gaze.

This paper addresses the face hallucination problem of converting thermal infrared face images into photo-realistic ones. It is a challenging task because the two modalities are of dramatical difference, which makes many developed linear models inapplicable. We propose a learning-based framework synthesizing the normal face from the infrared input. Compared to the previous work, we further exploit the local linearity in not only the image spatial domain but also the image manifolds. We have also developed a measurement of the variance between an input and its prediction, thus we can apply the Markov random field model to the predicted normal face to improve the hallucination result. Experimental results show the advantage of our algorithm over the existing methods. Our algorithm can be readily generalized to solve other multi-modal image conversion problems as well.