The physical properties of an object, such as mass, significantly affect how we manipulate it with our hands. Surprisingly, this aspect has so far been neglected in prior work on 3D motion synthesis. To improve the naturalness of the synthesized 3D hand-object motions, this work proposes MACS–the first MAss Conditioned 3D hand and object motion Synthesis approach. Our approach is based on cascaded diffusion models and generates interactions that plausibly adjust based on the object’s mass and interaction type. MACS also accepts a manually drawn 3D object trajectory as input and synthesizes the natural 3D hand motions conditioned by the object’s mass. This flexibility enables MACS to be used for various downstream applications, such as generating synthetic training data for ML tasks, fast animation of hands for graphics workflows, and generating character interactions for computer games. We show experimentally that a small-scale dataset is sufficient for MACS to reasonably generalize across interpolated and extrapolated object masses unseen during the training. Furthermore, MACS shows moderate generalization to unseen objects, thanks to the mass-conditioned contact labels generated by our surface contact synthesis model ConNet. Our comprehensive user study confirms that the synthesized 3D hand-object interactions are highly plausible and realistic.

In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultane-ously estimates human body and hand motion. This task presents significant challenges due to three factors: the lack of high-quality datasets, fisheye camera distortion, and hu-man body self-occlusion. To address these challenges, we propose a novel approach that leverages Fisheye ViT to ex-tract fisheye image features, which are subsequently con-verted into pixel-aligned 3D heatmap representations for 3D human body pose prediction. For hand tracking, we incorporate dedicated hand detection and hand pose esti-mation networks for regressing 3D hand poses. Finally, we develop a diffusion-based whole-body motion prior model to refine the estimated whole-body motion while accounting for joint uncertainties. To train these networks, we col-lect a large synthetic dataset, Ego WholeBody, comprising 840,000 high-quality egocentric images captured across a diverse range of whole-body motion sequences. Quantitative and qualitative evaluations demonstrate the effective-ness of our method in producing high-quality whole-body motion estimates from a single egocentric camera.

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.

Most existing point cloud upsampling methods have roughly three steps: feature extraction, feature expansion and 3D coordinate prediction. However, they usually suffer from two critical issues: (1) fixed upsampling rate after one-time training, since the feature expansion unit is customized for each upsampling rate; (2) outliers or shrinkage artifact caused by the difficulty of precisely predicting 3D coordinates or residuals of upsampled points. To adress them, we propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates. Our method first interpolates the low-res point cloud according to a given upsampling rate. And then refine the positions of the interpolated points with an iterative optimization process, guided by a trained model estimating the difference between the current point cloud and the high-res target. Extensive quantitative and qualitative results on benchmarks and downstream tasks demonstrate that our method achieves the state-of-the-art accuracy and efficiency.

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.

We propose sandwiched video compression – a video compression system that wraps neural networks around a standard video codec. The sandwich framework consists of a neural pre- and post-processor with a standard video codec between them. The networks are trained jointly to optimize a rate-distortion loss function with the goal of significantly improving over the standard codec in various compression scenarios. End-to-end training in this setting requires a differentiable proxy for the standard video codec, which incorporates temporal processing with motion compensation, inter/intra mode decisions, and in-loop filtering. We propose differentiable approximations to key video codec components and demonstrate that, in addition to providing meaningful compression improvements over the standard codec, the neural codes of the sandwich lead to significantly better rate-distortion performance in two important scenarios. When transporting high-resolution video via low-resolution HEVC, the sandwich system obtains 6.5 dB improvements over standard HEVC. More importantly, using the well-known perceptual similarity metric, LPIPS, we observe 30% improvements in rate at the same quality over HEVC. Last but not least, we show that pre- and post-processors formed by very modestly-parameterized, light-weight networks can closely approximate these results.

Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local density information. Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features. Specifically, we propose to encode local geometry and density with three embeddings: density embedding, local position embedding and ancestor embedding. During the decoding, we explicitly predict the upsampling factor for each point, and the directions and scales of the upsampled points. To mitigate the clustered points issue in existing methods, we design a novel sub-point convolution layer, and an upsampling block with adaptive scale. Furthermore, our method can also compress point-wise attributes, such as normal. Extensive qualitative and quantitative results on SemanticKITTI and ShapeNet demonstrate that our method achieves the state-of-the-art rate-distortion trade-off.

Given a standard image codec, we compress images that may have higher resolution and/or higher bit depth than allowed in the codec's specifications, by sandwiching the standard codec between a neural pre-processor (before the standard encoder) and a neural post-processor (after the standard decoder). Using a differentiable proxy for the the standard codec, we design the neural pre-and post-processors to transport the high resolution (super-resolution, SR) or high bit depth (high dynamic range, HDR) images as lower resolution and lower bit depth images. The neural processors accomplish this with spatially coded modulation, which acts as watermarks to preserve the important image detail during compression. Experiments show that compared to conventional methods of transmitting high resolution or high bit depth through lower resolution or lower bit depth codecs, our sandwich architecture gains ~9dB for SR images and $\sim$3dB for HDR images at the same rate over large test sets. We also observe significant gains in visual quality.

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 introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a hierarchy of latent grids, which can be decoded into different levels of detail and also achieve better accuracy. For shape completion, we propose latent grid dropout to simulate partial data in the latent space and therefore defer the completing functionality to the decoder side. This along with our multires design significantly improves the shape completion quality under decoder-only latent optimization. To the best of our knowledge, MDIF is the first deep implicit function model that can at the same time (1) represent different levels of detail and allow progressive decoding; (2) support both encoder-decoder inference and decoder-only latent optimization, and fulfill multiple applications; (3) perform detailed decoder-only shape completion. Experiments demonstrate its superior performance against prior art in various 3D reconstruction tasks.

We sandwich a standard image codec between two neural networks: a preprocessor that outputs neural codes, and a postprocessor that reconstructs the image. The neural codes are compressed as ordinary images by the standard codec. Using differentiable proxies for both rate and distortion, we develop a rate-distortion optimization framework that trains the networks to generate neural codes that are efficiently compressible as images. This architecture not only improves rate-distortion performance for ordinary RGB images, but also enables efficient compression of alternative image types (such as normal maps of computer graphics) using standard image codecs. Results demonstrate the effectiveness and flexibility of neural processing in mapping a variety of input data modalities to the rigid structure of standard codecs. A surprising result is that the rate-distortion-optimized neural processing seamlessly learns to transport color images using a single-channel (grayscale) codec.

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.

Hand pose estimation, formulated as an inverse problem, is typically optimized by an energy function over pose parameters using a 'black box' image generation procedure, knowing little about either the relationships between the parameters or the form of the energy function. In this paper, we show significant improvement upon such black box optimization by exploiting high-level knowledge of the parameter structure and using a local surrogate energy function. Our new framework, hierarchical sampling optimization (HSO), consists of a sequence of discriminative predictors organized into a kinematic hierarchy. Each predictor is conditioned on its ancestors, and generates a set of samples over a subset of the pose parameters, with only one selected by the highly-efficient surrogate energy. The selected partial poses are concatenated to generate a full-pose hypothesis. Repeating the same process, several hypotheses are generated and the full energy function selects the best result. Under the same kinematic hierarchy, two methods based on decision forest and convolutional neural network are proposed to generate the samples and two optimization methods are studied when optimizing these samples. Experimental evaluations on three publicly available datasets show that our method is particularly impressive in low-compute scenarios where it significantly outperforms all other state-of-the-art methods.

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.

In this paper we present Latent-Class Hough Forests, a method for object detection and 6 DoF pose estimation in heavily cluttered and occluded scenarios. We adapt a state of the art template matching feature into a scale-invariant patch descriptor and integrate it into a regression forest using a novel template-based split function. We train with positive samples only and we treat class distributions at the leaf nodes as latent variables. During testing we infer by iteratively updating these distributions, providing accurate estimation of background clutter and foreground occlusions and, thus, better detection rate. Furthermore, as a by-product, our Latent-Class Hough Forests can provide accurate occlusion aware segmentation masks, even in the multi-instance scenario. In addition to an existing public dataset, which contains only single-instance sequences with large amounts of clutter, we have collected two, more challenging, datasets for multiple-instance detection containing heavy 2D and 3D clutter as well as foreground occlusions. We provide extensive experiments on the various parameters of the framework such as patch size, number of trees and number of iterations to infer class distributions at test time. We also evaluate the Latent-Class Hough Forests on all datasets where we outperform state of the art methods.

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.

In this paper we present the latent regression forest (LRF), a novel framework for real-time, 3D hand pose estimation from a single depth image. Prior discriminative methods often fall into two categories: holistic and patch-based. Holistic methods are efficient but less flexible due to their nearest neighbour nature. Patch-based methods can generalise to unseen samples by consider local appearance only. However, they are complex because each pixel need to be classified or regressed during testing. In contrast to these two baselines, our method can be considered as a structured coarse-to-fine search, starting from the centre of mass of a point cloud until locating all the skeletal joints. The searching process is guided by a learnt latent tree model which reflects the hierarchical topology of the hand. Our main contributions can be summarised as follows: (i) Learning the topology of the hand in an unsupervised, data-driven manner. (ii) A new forest-based, discriminative framework for structured search in images, as well as an error regression step to avoid error accumulation. (iii) A new multi-view hand pose dataset containing 180 K annotated images from 10 different subjects. Our experiments on two datasets show that the LRF outperforms baselines and prior arts in both accuracy and efficiency.

The state of the art in articulated hand tracking has been greatly advanced by hybrid methods that fit a generative hand model to depth data, leveraging both temporally and discriminatively predicted starting poses. In this paradigm, the generative model is used to define an energy function and a local iterative optimization is performed from these starting poses in order to find a "good local minimum" (i.e. a local minimum close to the true pose). Performing this optimization quickly is key to exploring more starting poses, performing more iterations and, crucially, exploiting high frame rates that ensure that temporally predicted starting poses are in the basin of convergence of a good local minimum. At the same time, a detailed and accurate generative model tends to deepen the good local minima and widen their basins of convergence. Recent work, however, has largely had to trade-off such a detailed hand model with one that facilitates such rapid optimization. We present a new implicit model of hand geometry that mostly avoids this compromise and leverage it to build an ultra-fast hybrid hand tracking system. Specifically, we construct an articulated signed distance function that, for any pose, yields a closed form calculation of both the distance to the detailed surface geometry and the necessary derivatives to perform gradient based optimization. There is no need to introduce or update any explicit "correspondences" yielding a simple algorithm that maps well to parallel hardware such as GPUs. As a result, our system can run at extremely high frame rates (e.g. up to 1000fps). Furthermore, we demonstrate how to detect, segment and optimize for two strongly interacting hands, recovering complex interactions at extremely high framerates. In the absence of publicly available datasets of sufficiently high frame rate, we leverage a multiview capture system to create a new 180fps dataset of one and two hands interacting together or with objects.

We address the problem of hand pose estimation, formulated as an inverse problem. Typical approaches optimize an energy function over pose parameters using a 'black box' image generation procedure. This procedure knows little about either the relationships between the parameters or the form of the energy function. In this paper, we show that we can significantly improving upon black box optimization by exploiting high-level knowledge of the structure of the parameters and using a local surrogate energy function. Our new framework, hierarchical sampling optimization, consists of a sequence of predictors organized into a kinematic hierarchy. Each predictor is conditioned on its ancestors, and generates a set of samples over a subset of the pose parameters. The highly-efficient surrogate energy is used to select among samples. Having evaluated the full hierarchy, the partial pose samples are concatenated to generate a full-pose hypothesis. Several hypotheses are generated using the same procedure, and finally the original full energy function selects the best result. Experimental evaluation on three publically available datasets show that our method is particularly impressive in low-compute scenarios where it significantly outperforms all other state-of-the-art methods.

Faces in the wild are usually captured with various poses, illuminations and occlusions, and thus inherently multimodally distributed in many tasks. We propose a conditional Convolutional Neural Network, named as c-CNN, to handle multimodal face recognition. Different from traditional CNN that adopts fixed convolution kernels, samples in c-CNN are processed with dynamically activated sets of kernels. In particular, convolution kernels within each layer are only sparsely activated when a sample is passed through the network. For a given sample, the activations of convolution kernels in a certain layer are conditioned on its present intermediate representation and the activation status in the lower layers. The activated kernels across layers define the sample-specific adaptive routes that reveal the distribution of underlying modalities. Consequently, the proposed framework does not rely on any prior knowledge of modalities in contrast with most existing methods. To substantiate the generic framework, we introduce a special case of c-CNN via incorporating the conditional routing of the decision tree, which is evaluated with two problems of multimodality - multi-view face identification and occluded face verification. Extensive experiments demonstrate consistent improvements over the counterparts unaware of modalities.

In this paper we present the Latent Regression Forest (LRF), a novel framework for real-time, 3D hand pose estimation from a single depth image. In contrast to prior forest-based methods, which take dense pixels as input, classify them independently and then estimate joint positions afterwards, our method can be considered as a structured coarse-to-fine search, starting from the centre of mass of a point cloud until locating all the skeletal joints. The searching process is guided by a learnt Latent Tree Model which reflects the hierarchical topology of the hand. Our main contributions can be summarised as follows: (i) Learning the topology of the hand in an unsupervised, data-driven manner. (ii) A new forest-based, discriminative framework for structured search in images, as well as an error regression step to avoid error accumulation. (iii) A new multi-view hand pose dataset containing 180K annotated images from 10 different subjects. Our experiments show that the LRF out-performs state-of-the-art methods in both accuracy and efficiency.

This paper presents the first semi-supervised transductive algorithm for real-time articulated hand pose estimation. Noisy data and occlusions are the major challenges of articulated hand pose estimation. In addition, the discrepancies among realistic and synthetic pose data undermine the performances of existing approaches that use synthetic data extensively in training. We therefore propose the Semi-supervised Transductive Regression (STR) forest which learns the relationship between a small, sparsely labelled realistic dataset and a large synthetic dataset. We also design a novel data-driven, pseudo-kinematic technique to refine noisy or occluded joints. Our contributions include: (i) capturing the benefits of both realistic and synthetic data via transductive learning, (ii) showing accuracies can be improved by considering unlabelled data, and (iii) introducing a pseudo-kinematic technique to refine articulations efficiently. Experimental results show not only the promising performance of our method with respect to noise and occlusions, but also its superiority over state-of-the-arts in accuracy, robustness and speed.

In this paper, we present a new pedestrian detection method combining Random Forest and Dominant Orientation Templates(DOT) to achieve state-of-the-art accuracy and, more importantly, to accelerate run-time speed. DOT can be considered as a binary version of Histogram of Oriented Gradients(HOG) and therefore provides time-efficient properties. However, since discarding magnitude information, it degrades the detection rate, when it is directly incorporated. We propose a novel template-matching split function using DOT for Random Forest. It divides a feature space in a non-linear manner, but has a very low complexity up to binary bit-wise operations. Experiments demonstrate that our method provides much superior speed with comparable accuracy to state-ofthe-art pedestrian detectors. By combining a holistic and a patch-based detectors in a cascade manner, we accelerate the detection speed of Hough Forest, a prior-art using Random Forest and HOG, by about 20 times. The obtained speed is 5 frames per second for 640×480 images with 24 scales.