HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map
TU Kaiserslautern（凯泽斯劳滕工业大学）；DFKI Kaiserslautern（德国人工智能研究中心凯泽斯劳滕分部）；NUST Pakistan（巴基斯坦国家科技大学）；UPM Saudi Arabia（沙特阿拉伯穆罕默德·本·法赫德王子大学）；MPII Saarland（马克斯·普朗克信息学研究所）
Jameel Malik, Ibrahim Abdelaziz, Ahmed Elhayek, Soshi Shimada, Sk Aziz Ali, Vladislav Golyanik, Christian Theobalt, Didier Stricker
3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. The state-of-the-art methods directly regress 3D hand meshes from 2D depth images via 2D convolutional neural networks, which leads to artefacts in the estimations due to perspective distortions in the images. In contrast, we propose a novel architecture with 3D convolutions trained in a weakly-supervised manner. The input to our method is a 3D voxelized depth map, and we rely on two hand shape representations. The first one is the 3D voxelized grid of the shape which is accurate but does not preserve the mesh topology and the number of mesh vertices. The second representation is the 3D hand surface which is less accurate but does not suffer from the limitations of the first representation. We combine the advantages of these two representations by registering the hand surface to the voxelized hand shape. In the extensive experiments, the proposed approach improves over the state of the art by 47.8% on the SynHand5M dataset. Moreover, our augmentation policy for voxelized depth maps further enhances the accuracy of 3D hand pose estimation on real data. Our method produces visually more reasonable and realistic hand shapes on NYU and BigHand2.2M datasets compared to the existing approaches.
TU Kaiserslautern（凯泽斯劳滕工业大学）；DFKI（德国人工智能研究中心）；NUST Pakistan（巴基斯坦国立科技大学）；UPM Saudi Arabia（沙特阿拉伯乌姆·库拉大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）
3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. Existing methods addressing it directly regress hand meshes via 2D convolutional neural networks, which leads to artefacts due to perspective distortions in the images. To address the limitations of the existing methods, we develop HandVoxNet++, i.e., a voxel-based deep network with 3D and graph convolutions trained in a fully supervised manner. The input to our network is a 3D voxelized-depth-map-based on the truncated signed distance function (TSDF). HandVoxNet++…
Microsoft Research Asia（微软亚洲研究院）；Huazhong University of Science and Technology（华中科技大学）
We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estimate 3D poses and re-identification (Re-ID) features for all people in the environment. In contrast to previous efforts which require to establish cross-view correspondence based on noisy 2D pose estimates, it directly estimates and tracks 3D poses from a 3D voxel-based representation constructed from multi-view images. We first discretize the 3D space by regular voxels and compute a feature vector for each voxel by av…
Seoul National University（首尔大学）；Kwangwoon University（光云大学）
Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs). The first weakness of this approach is the presence of perspective distortion in the 2D depth map. While the depth map is intrinsically 3D data, many previous methods treat depth maps as 2D images that can distort the shape of the actual object through projection from 3D to 2D space. This compe…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）
While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes. We present Faster VoxelPose to address the challenge by re-projecting the feature volume to the three two-dimensional coordinate planes and estimating X, Y, Z coordinates from them separately. To that end, we first localize each person by a 3D bounding box by estimating a 2D box and its height based on the volume features projected to the xy-plane and z-axis, respectively. Then for each person, we estimate…
Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）
We present an approach to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we present an end-to-end solution which directly operates in the $3$D space, therefore avoids making incorrect decisions in the 2D space. To achieve this goal, the features in all camera views are warped and aggregated in a common 3D space, and fed into Cuboid Proposal Network (CPN) to coarsely localize all people. Then we propose Pose Regression Network (PRN) to est…
The Chinese University of Hong Kong（香港中文大学）；The Hong Kong Polytechnic University（香港理工大学）
In this paper, we propose a novel structure-aware 3D hourglass network for hand pose estimation from a single depth image, which achieves state-of-the-art results on MSRA and NYU datasets. Compared to existing works that perform image-to-coordination regression, our network takes 3D voxel as input and directly regresses 3D heatmap for each joint. To be specific, we use hourglass network as our backbone network and modify it into 3D form. We explicitly model tree-like finger bone into the network as well as in the loss function in an end-to-end manner, in order to take the skeleton constraints …
Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Pointwise Rotation-Invariant Network, focusing on rotation-invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. In addition, we propose Spherical Voxel Convolution and Point Re-sampling to extract rotation-invariant features for each point. Our netwo…
Semantic Occupancy Prediction with Dual Range-Voxel Representation
School of Software Engineering, South China University of Technology（华南理工大学软件学院）；State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, CAS（中国科学院光电技术研究所光学场操控科学与技术国家重点实验室）
The task of reconstructing detailed 3D human body models from images is interesting but challenging in computer vision due to the high freedom of human bodies. In order to tackle the problem, we propose a coarse-to-fine method to reconstruct a detailed 3D human body from multi-view images combining voxel super-resolution based on learning the implicit representation. Firstly, the coarse 3D models are estimated by learning an implicit representation based on multi-scale features which are extracted by multi-stage hourglass networks from the multi-view images. Then, taking the low resolution vox…
ASRI, Seoul National University（首尔国立大学自动化与系统研究所）；Kwangwoon University（光云大学）
We propose a novel approach to 3D human pose estimation from a single depth map. Recently, convolutional neural network (CNN) has become a powerful paradigm in computer vision. Many of computer vision tasks have benefited from CNNs, however, the conventional approach to directly regress 3D body joint locations from an image does not yield a noticeably improved performance. In contrast, we formulate the problem as estimating per-voxel likelihood of key body joints from a 3D occupancy grid. We argue that learning a mapping from volumetric input to volumetric output with 3D convolution consistent…
Indian Institute of Information Technology Pune（印度信息技术学院浦那分院）
Hand pose estimation from monocular depth images has been an important and challenging problem in the Computer Vision community. In this paper, we present a novel approach to estimate 3D hand joint locations from 2D depth images. Unlike most of the previous methods, our model captures the 3D spatial information from a depth image thereby giving it a greater understanding of the input. We voxelize the input depth map to capture the 3D features of the input and perform 3D data augmentations to make our network robust to real-world images. Our network is trained in an end-to-end manner which redu…
We present Gradient-SDF, a novel representation for 3D geometry that combines the advantages of implict and explicit representations. By storing at every voxel both the signed distance field as well as its gradient vector field, we enhance the capability of implicit representations with approaches originally formulated for explicit surfaces. As concrete examples, we show that (1) the Gradient-SDF allows us to perform direct SDF tracking from depth images, using efficient storage schemes like hash maps, and that (2) the Gradient-SDF representation enables us to perform photometric bundle adjust…
A major element of depth perception and 3D understanding is the ability to predict the 3D layout of a scene and its contained objects for a novel pose. Indoor environments are particularly suitable for novel view prediction, since the set of objects in such environments is relatively restricted. In this work we address the task of 3D prediction especially for indoor scenes by leveraging only weak supervision. In the literature 3D scene prediction is usually solved via a 3D voxel grid. However, such methods are limited to estimating rather coarse 3D voxel grids, since predicting entire voxel sp…
South China University of Technology（华南理工大学）；University of Oulu（奥卢大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
State-of-the-art single depth image-based 3D hand pose estimation methods are based on dense predictions, including voxel-to-voxel predictions, point-to-point regression, and pixel-wise estimations. Despite the good performance, those methods have a few issues in nature, such as the poor trade-off between accuracy and efficiency, and plain feature representation learning with local convolutions. In this paper, a novel pixel-wise prediction-based method is proposed to address the above issues. The key ideas are two-fold: a) explicitly modeling the dependencies among joints and the relations bet…
In this paper we presented mmPose-NLP, a novel Natural Language Processing (NLP) inspired Sequence-to-Sequence (Seq2Seq) skeletal key-point estimator using millimeter-wave (mmWave) radar data. To the best of the author's knowledge, this is the first method to precisely estimate upto 25 skeletal key-points using mmWave radar data alone. Skeletal pose estimation is critical in several applications ranging from autonomous vehicles, traffic monitoring, patient monitoring, gait analysis, to defense security forensics, and aid both preventative and actionable decision making. The use of mmWave radar…
Technical University of Munich（慕尼黑工业大学）；German Aerospace Center（德国航空航天中心）
Recently, 3D input data based hand pose estimation methods have shown state-of-the-art performance, because 3D data capture more spatial information than the depth image. Whereas 3D voxel-based methods need a large amount of memory, PointNet based methods need tedious preprocessing steps such as K-nearest neighbour search for each point. In this paper, we present a novel deep learning hand pose estimation method for an unordered point cloud. Our method takes 1024 3D points as input and does not require additional information. We use Permutation Equivariant Layer (PEL) as the basic element, whe…
ShapeGraFormer: GraFormer-Based Network for Hand-Object Reconstruction from a Single Depth Map
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；University of Kaiserslautern-Landau (RPTU)（凯泽斯劳滕-兰道大学）；National University of Sciences and Technology (NUST)（国家科技大学）；University of Prince Mugrin (UPM)（穆格林王子大学）
In modern visual SLAM systems, it is a standard practice to retrieve potential candidate map points from overlapping keyframes for further feature matching or direct tracking. In this work, we argue that keyframes are not the optimal choice for this task, due to several inherent limitations, such as weak geometric reasoning and poor scalability. We propose a voxel-map representation to efficiently retrieve map points for visual SLAM. In particular, we organize the map points in a regular voxel grid. Visible points from a camera pose are queried by sampling the camera frustum in a raycasting ma…
3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly training 3D object detection and monocular dense depth reconstruction neural networks. It takes as inputs, a LiDAR point-cloud, and a single RGB image during inference and produces object pose predictions as well as a densely reconstructed depth map. LiDAR point-cloud is converted into a set of voxels, and its features are extracted using 3D convolution layers, f…
Nanjing University of Science & Technology（南京理工大学）；The Hong Kong University of Science & Technology（香港科技大学）；Nanyang Technological University（南洋理工大学）；Singapore Management University（新加坡管理大学）
Semantic Scene Completion (SSC) transforms an image of single-view depth and/or RGB 2D pixels into 3D voxels, each of whose semantic labels are predicted. SSC is a well-known ill-posed problem as the prediction model has to "imagine" what is behind the visible surface, which is usually represented by Truncated Signed Distance Function (TSDF). Due to the sensory imperfection of the depth camera, most existing methods based on the noisy TSDF estimated from depth values suffer from 1) incomplete volumetric predictions and 2) confused semantic labels. To this end, we use the ground-truth 3D voxels…
Recent work has shown good recognition results in 3D object recognition using 3D convolutional networks. In this paper, we show that the object orientation plays an important role in 3D recognition. More specifically, we argue that objects induce different features in the network under rotation. Thus, we approach the category-level classification task as a multi-task problem, in which the network is trained to predict the pose of the object in addition to the class label as a parallel task. We show that this yields significant improvements in the classification results. We test our suggested a…
In this paper, we develop novel, efficient 2D encodings for 3D geometry, which enable reconstructing full 3D shapes from a single image at high resolution. The key idea is to pose 3D shape reconstruction as a 2D prediction problem. To that end, we first develop a simple baseline network that predicts entire voxel tubes at each pixel of a reference view. By leveraging well-proven architectures for 2D pixel-prediction tasks, we attain state-of-the-art results, clearly outperforming purely voxel-based approaches. We scale this baseline to higher resolutions by proposing a memory-efficient shape e…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
We present Multi-Garment Network (MGN), a method to predict body shape and clothing, layered on top of the SMPL model from a few frames (1-8) of a video. Several experiments demonstrate that this representation allows higher level of control when compared to single mesh or voxel representations of shape. Our model allows to predict garment geometry, relate it to the body shape, and transfer it to new body shapes and poses. To train MGN, we leverage a digital wardrobe containing 712 digital garments in correspondence, obtained with a novel method to register a set of clothing templates to a dat…
The conventional pose estimation of a 3D object usually requires the knowledge of the 3D model of the object. Even with the recent development in convolutional neural networks (CNNs), a 3D model is often necessary in the final estimation. In this paper, we propose a two-stage pipeline that takes in raw colored point cloud data and estimates an object's translation and rotation by running 3D convolutions on voxels. The pipeline is simple yet highly accurate: translation error is reduced to the voxel resolution (around 1 cm) and rotation error is around 5 degrees. The pipeline is also put to act…
We introduce Hybrid Bayesian Eigenobjects (HBEOs), a novel representation for 3D objects designed to allow a robot to jointly estimate the pose, class, and full 3D geometry of a novel object observed from a single viewpoint in a single practical framework. By combining both linear subspace methods and deep convolutional prediction, HBEOs efficiently learn nonlinear object representations without directly regressing into high-dimensional space. HBEOs also remove the onerous and generally impractical necessity of input data voxelization prior to inference. We experimentally evaluate the suitabil…
University of Pennsylvania（宾夕法尼亚大学）；Ryerson University（瑞尔森大学）
This paper addresses the challenge of 3D human pose estimation from a single color image. Despite the general success of the end-to-end learning paradigm, top performing approaches employ a two-step solution consisting of a Convolutional Network (ConvNet) for 2D joint localization and a subsequent optimization step to recover 3D pose. In this paper, we identify the representation of 3D pose as a critical issue with current ConvNet approaches and make two important contributions towards validating the value of end-to-end learning for this task. First, we propose a fine discretization of the 3D …
University of Bologna（博洛尼亚大学）；Google Inc.（谷歌公司）；Technische Universität München（慕尼黑工业大学）
Estimating the 3D shape of an object from a single or multiple images has gained popularity thanks to the recent breakthroughs powered by deep learning. Most approaches regress the full object shape in a canonical pose, possibly extrapolating the occluded parts based on the learned priors. However, their viewpoint invariant technique often discards the unique structures visible from the input images. In contrast, this paper proposes to rely on viewpoint variant reconstructions by merging the visible information from the given views. Our approach is divided into three steps. Starting from the s…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Facebook AI Research（Facebook人工智能研究院）；National University of Singapore（新加坡国立大学）
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have demonstrated promising results by learning scene representations that implicitly encode both geometry and appearance without 3D supervision. However, existing approaches in practice often show blurry renderings caused by the limited network capacity or the difficulty in finding accurate intersections of camera rays with the scene geometry. Synthesizing high-reso…
Institute of Science and Technology (IST) Austria（奥地利科学技术研究所）；Google Research（谷歌研究院）
We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches rely on 3D supervision, annotation of 2D images with keypoints or poses, and/or training with multiple views of each object instance. Our framework is very general: it can be trained in similar settings to existing approaches, while also supporting weaker supervision. Importantly, it can be trained purely from 2D images, without pose annotations, and with o…
Simon Fraser University（西蒙菲莎大学）；University of Regina（里贾纳大学）
We present a generalized grasping algorithm that uses point clouds (i.e. a group of points and their respective surface normals) to discover grasp pose solutions for multiple grasp types, executed by a mechanical gripper, in near real-time. The algorithm introduces two ideas: 1) a histogram of finger contact normals is used to represent a grasp 'shape' to guide a gripper orientation search in a histogram of object(s) surface normals, and 2) voxel grid representations of gripper and object(s) are cross-correlated to match finger contact points, i.e. grasp 'size', to discover a grasp pose. Const…
University of Edinburgh（爱丁堡大学）；Google Research（谷歌研究院）
We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, existing approaches rely on 3D supervision, annotation of 2D images with keypoints or poses, and/or training with multiple views of each object instance. Our framework is very general: it can be trained in similar settings to these existing approaches, while also supporting weaker supervision scenarios. Importantly, it can be trained purely from 2D images, without ground-truth pose…
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. In this paper we propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid as it combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN ar…
Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D features for subsequent tasks. For example, the 3D features can be taken as input for not only detection, but also end-to-end prediction and/or planning that require a bird's-eye-view feature representation. In the study, we found that in generating 3D representation previous methods do not maintain the consistency between the objects' implicit poses in the laten…
Vanderbilt University（范德堡大学）；Middle Tennessee State University（中田纳西州立大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
Diffusion-weighted magnetic resonance imaging (DW-MRI) allows for non-invasive imaging of the local fiber architecture of the human brain at a millimetric scale. Multiple classical approaches have been proposed to detect both single (e.g., tensors) and multiple (e.g., constrained spherical deconvolution, CSD) fiber population orientations per voxel. However, existing techniques generally exhibit low reproducibility across MRI scanners. Herein, we propose a data-driven tech-nique using a neural network design which exploits two categories of data. First, training data were acquired on three squ…
3D reconstruction is a core task in many applications such as robot navigation or sites inspections. Finding the best poses to capture part of the scene is one of the most challenging topic that goes under the name of Next Best View. Recently, many volumetric methods have been proposed; they choose the Next Best View by reasoning over a 3D voxelized space and by finding which pose minimizes the uncertainty decoded into the voxels. Such methods are effective, but they do not scale well since the underlaying representation requires a huge amount of memory. In this paper we propose a novel mesh-b…
Computer Science Department, University College London（伦敦大学学院计算机科学系）
3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs. An equivariant representation vector has two components: the invariant identity part, and a discernable encoding of the transformation. Models that can't explain pose-differences r…
We present an approach to perform 3D pose estimation of multiple people from a few calibrated camera views. Our architecture, leveraging the recently proposed unprojection layer, aggregates feature-maps from a 2D pose estimator backbone into a comprehensive representation of the 3D scene. Such intermediate representation is then elaborated by a fully-convolutional volumetric network and a decoding stage to extract 3D skeletons with sub-voxel accuracy. Our method achieves state of the art MPJPE on the CMU Panoptic dataset using a few unseen views and obtains competitive results even with a sing…
In this paper, we introduce 3D-GMNet, a deep neural network for 3D object shape reconstruction from a single image. As the name suggests, 3D-GMNet recovers 3D shape as a Gaussian mixture. In contrast to voxels, point clouds, or meshes, a Gaussian mixture representation provides an analytical expression with a small memory footprint while accurately representing the target 3D shape. At the same time, it offers a number of additional advantages including instant pose estimation and controllable level-of-detail reconstruction, while also enabling interpretation as a point cloud, volume, and a mes…
