3D Hand Pose Research Articles

MPCTrans: Multi-Perspective Cue-Aware Joint Relationship Representation for 3D Hand Pose Estimation via Swin Transformer.

The objective of 3D hand pose estimation (HPE) based on depth images is to accurately locate and predict keypoints of the hand. However, this task remains challenging because of the variations in hand appearance from different viewpoints and severe occlusions. To effectively address these challenges, this study introduces a novel approach, called the multi-perspective cue-aware joint relationship representation for 3D HPE via the Swin Transformer (MPCTrans, for short). This approach is designed to learn multi-perspective cues and essential information from hand depth images. To achieve this goal, three novel modules are proposed to utilize features from multiple virtual views of the hand, namely, the adaptive virtual multi-viewpoint (AVM), hierarchy feature estimation (HFE), and virtual viewpoint evaluation (VVE) modules. The AVM module adaptively adjusts the angles of the virtual viewpoint and learns the ideal virtual viewpoint to generate informative multiple virtual views. The HFE module estimates hand keypoints through hierarchical feature extraction. The VVE module evaluates virtual viewpoints by using chained high-level functions from the HFE module. Transformer is used as a backbone to extract the long-range semantic joint relationships in hand depth images. Extensive experiments demonstrate that the MPCTrans model achieves state-of-the-art performance on four challenging benchmark datasets.

Using 3D Hand Pose Data in Recognizing Human–Object Interaction and User Identification for Extended Reality Systems

Object detection and action/gesture recognition have become imperative in security and surveillance fields, finding extensive applications in everyday life. Advancement in such technologies will help in furthering cybersecurity and extended reality systems through the accurate identification of users and their interactions, which plays a pivotal role in the security management of an entity and providing an immersive experience. Essentially, it enables the identification of human–object interaction to track actions and behaviors along with user identification. Yet, it is performed by traditional camera-based methods with high difficulties and challenges since occlusion, different camera viewpoints, and background noise lead to significant appearance variation. Deep learning techniques also demand large and labeled datasets and a large amount of computational power. In this paper, a novel approach to the recognition of human–object interactions and the identification of interacting users is proposed, based on three-dimensional hand pose data from an egocentric camera view. A multistage approach that integrates object detection with interaction recognition and user identification using the data from hand joints and vertices is proposed. Our approach uses a statistical attribute-based model for feature extraction and representation. The proposed technique is tested on the HOI4D dataset using the XGBoost classifier, achieving an average F1-score of 81% for human–object interaction and an average F1-score of 80% for user identification, hence proving to be effective. This technique is mostly targeted for extended reality systems, as proper interaction recognition and users identification are the keys to keeping systems secure and personalized. Its relevance extends into cybersecurity, augmented reality, virtual reality, and human–robot interactions, offering a potent solution for security enhancement along with enhancing interactivity in such systems.

DM-HAP: Diffusion model for accurate hand pose prediction

Forecasting hand poses is a challenging task due to inherent uncertainties, occlusions, and inaccuracies in 3D pose estimation. Diffusion models provide a promising direction for predicting precise 3D hand poses under noisy conditions. In this work, we introduce Dual-diffusion, an innovative framework for the precise prediction of future hand poses. Our approach leverages the strengths of diffusion models by framing hand pose forecasting as a reverse diffusion process, effectively addressing the complexities of noisy hand joint movements and their subtleties. To enhance the learning of hand pose representations, we propose a unique neural architecture that simultaneously captures both local and global features. This is achieved through the deployment of Global and Local Diffusion (GLD) blocks within our network, which facilitate the exchange of information between local and global features. This diffusion-based interaction enables the integration of global hand actions and local finger actions, leading to a more powerful representation learning approach. We evaluate the effectiveness of our Dual-diffusion method on three public 3D hand pose estimation datasets (MSRA, F-PHAB, and BigHand2.2M), and our approach outperforms previous methods.

Progressively global–local fusion with explicit guidance for accurate and robust 3d hand pose reconstruction

Parametric and non-parametric methods are two commonly used strategies in current 3D hand pose reconstruction. Parametric methods predict low-dimensional parameters to fit a predefined hand model to the input image. Benefiting from the prior knowledge of hand models, parametric methods guarantee plausible hand poses, whereas the pose estimation accuracy is limited due to nonlinear regression and spatial information loss. Differently, non-parametric methods directly estimate the coordinates of keypoints or mesh vertices from the input image. The reconstructed 3D hand poses show high precision but may be less robust. In this paper, we integrate the advantages of two methods for accurate and robust hand pose reconstruction. Specifically, we disentangle the hand pose reconstruction into global modeling and local refinement, which is performed in a coarse-to-fine manner. Firstly, we utilize global features from the encoder to generate the initial estimation by a parametric method, which aims to provide the prior knowledge of the human hand for subsequent processes. Then, we gradually fuse multi-scale contextual features for local refinement by explicitly integrating global prior information and local visual features. In particular, we introduce a consecutive pixel-aligned feature retrieval module to extract fine-grained information from visual features, thereby achieving pixel-level alignment. Furthermore, we demonstrate that our method can be extended to weakly-supervised learning where only sparse pose annotations are needed, potentially alleviating the burden of meticulous mesh annotation. The effectiveness and robustness of our method are substantiated through both fully- and weakly-supervised experiments, demonstrating superior performance compared to state-of-the-art methods. We plan to release our code at https://github.com/Kun-Gao/P_GLFnet.

EvHandPose: Event-Based 3D Hand Pose Estimation With Sparse Supervision.

Event camera shows great potential in 3D hand pose estimation, especially addressing the challenges of fast motion and high dynamic range in a low-power way. However, due to the asynchronous differential imaging mechanism, it is challenging to design event representation to encode hand motion information especially when the hands are not moving (causing motion ambiguity), and it is infeasible to fully annotate the temporally dense event stream. In this paper, we propose EvHandPose with novel hand flow representations in Event-to-Pose module for accurate hand pose estimation and alleviating the motion ambiguity issue. To solve the problem under sparse annotation, we design contrast maximization and hand-edge constraints in Pose-to-IWE (Image with Warped Events) module and formulate EvHandPose in a weakly-supervision framework. We further build EvRealHands, the first large-scale real-world event-based hand pose dataset on several challenging scenes to bridge the real-synthetic domain gap. Experiments on EvRealHands demonstrate that EvHandPose outperforms previous event-based methods under all evaluation scenes, achieves accurate and stable hand pose estimation with high temporal resolution in fast motion and strong light scenes compared with RGB-based methods, generalizes well to outdoor scenes and another type of event camera, and shows the potential for the hand gesture recognition task.

Enhancing 3D hand pose estimation using SHaF: synthetic hand dataset including a forearm

Enhancing 3D hand pose estimation using SHaF: synthetic hand dataset including a forearm

Towards Smartphone-based 3D Hand Pose Reconstruction Using Acoustic Signals

Accurately reconstructing 3D hand poses is a pivotal element for numerous Human-Computer Interaction applications. In this work, we propose SonicHand, the first Smartphone-based 3D Hand Pose Reconstruction system using purely inaudible acoustic signals. SonicHand incorporates signal processing techniques and a deep learning framework to address a series of challenges. Firstly, it encodes the topological information of the hand skeleton as prior knowledge and utilizes a deep learning model to realistically and smoothly reconstruct the hand poses. Secondly, the system employs adversarial training to enhance the generalization ability of our system to be deployed in a new environment or for a new user. Thirdly, we adopt a hand tracking method based on channel impulse response (CIR) estimation. It enables our system to handle the scenario where the hand performs gestures while moving arbitrarily as a whole. We conduct extensive experiments on a smartphone testbed to demonstrate the effectiveness and robustness of our system from various dimensions. The experiments involve 10 subjects performing up to 12 different hand gestures in 3 distinctive environments. When the phone is held in one of the user’s hand, the proposed system can track joints with an average error of 18.64 mm.

Simulation-driven design of smart gloves for gesture recognition

Smart gloves are in high demand for entertainment, manufacturing, and rehabilitation. However, designing smart gloves has been complex and costly due to trial and error. We propose an open simulation platform for designing smart gloves, including optimal sensor placement and deep learning models for gesture recognition, with reduced costs and manual effort. Our pipeline starts with 3D hand pose extraction from videos and extends to the refinement and conversion of the poses into hand joint angles based on inverse kinematics, the sensor placement optimization based on hand joint analysis, and the training of deep learning models using simulated sensor data. In comparison to the existing platforms that always require precise motion data as input, our platform takes monocular videos, which can be captured with widely available smartphones or web cameras, as input and integrates novel approaches to minimize the impact of the errors induced by imprecise motion extraction from videos. Moreover, our platform enables more efficient sensor placement selection. We demonstrate how the pipeline works and how it delivers a sensible design for smart gloves in a real-life case study. We also evaluate the performance of each building block and its impact on the reliability of the generated design.

3D hand pose and mesh estimation via a generic Topology-aware Transformer model.

In Human-Robot Interaction (HRI), accurate 3D hand pose and mesh estimation hold critical importance. However, inferring reasonable and accurate poses in severe self-occlusion and high self-similarity remains an inherent challenge. In order to alleviate the ambiguity caused by invisible and similar joints during HRI, we propose a new Topology-aware Transformer network named HandGCNFormer with depth image as input, incorporating prior knowledge of hand kinematic topology into the network while modeling long-range contextual information. Specifically, we propose a novel Graphformer decoder with an additional Node-offset Graph Convolutional layer (NoffGConv). The Graphformer decoder optimizes the synergy between the Transformer and GCN, capturing long-range dependencies and local topological connections between joints. On top of that, we replace the standard MLP prediction head with a novel Topology-aware head to better exploit local topological constraints for more reasonable and accurate poses. Our method achieves state-of-the-art 3D hand pose estimation performance on four challenging datasets, including Hands2017, NYU, ICVL, and MSRA. To further demonstrate the effectiveness and scalability of our proposed Graphformer Decoder and Topology aware head, we extend our framework to HandGCNFormer-Mesh for the 3D hand mesh estimation task. The extended framework efficiently integrates a shape regressor with the original Graphformer Decoder and Topology aware head, producing Mano parameters. The results on the HO-3D dataset, which contains various and challenging occlusions, show that our HandGCNFormer-Mesh achieves competitive results compared to previous state-of-the-art 3D hand mesh estimation methods.

A Normalization Strategy for Weakly Supervised 3D Hand Pose Estimation

The effectiveness of deep neural network models is intricately tied to the distribution of training data. However, in pose estimation, potential discrepancies in root joint positions and inherent variability in biomechanical features across datasets are often overlooked in current training strategies. To address these challenges, a novel Hand Pose Biomechanical Model (HPBM) is developed. In contrast to the traditional 3D coordinate-encoded pose, it provides a more intuitive depiction of the anatomical characteristics of the hand. Through this model, a data normalization approach is implemented to align the root joint and unify the biomechanical features of training samples. Furthermore, the HPBM facilitates a weakly supervised strategy for dataset expansion, significantly enhancing the data diversity. The proposed normalized method is evaluated on two widely used 3D hand pose estimation datasets, RHD and STB, demonstrating superior performance compared to the models trained without normalized datasets. Utilizing ground truth 2D keypoints as input, a reduction of 45.1% and 43.4% in error is achieved on the STB and RHD datasets, respectively. When leveraging 2D keypoints from MediaPipe, a reduction in error by 11.3% and 14.3% is observed on the STB and RHD datasets.

3D hand pose estimation and reconstruction based on multi-feature fusion

3D hand pose estimation and shape reconstruction is to recover the hand joint points and hand mesh vertices coordinates from the image. However, existing methods usually only use the high-level semantic features extracted by the backbone network to represent the hand mesh vertex features, which leads to a single representation of the hand vertices features and cannot fully utilize the feature information extracted by the network. In this paper, we propose a method for real-time 3D reconstruction of hands from a single RGB image, which enriches the 3D semantic information of the mesh vertices through multi-feature fusion. Firstly, we regress the 2D features of mesh vertices through Integral Pose Regression (IPR) and regard them as prior information to 3D features. Then we design a Multi-Scale Sampling(MSS) module to extract multi-scale information. Finally we fuse 2D prior features, multi-scale features, and high-level semantic features extracted by backbone to represent 3D initial feature. Additionally, we propose a Multi-Root(MR) loss function to address the imbalance problem caused by a single root joint. The experimental results indicate that our network achieves competitive performance on the FreiHAND and HO-3D public datasets, achieving fast inference speed with fewer parameters.

BaSICNet: Lightweight 3-D Hand Pose Estimation Network Based on Biomechanical Structure Information for Dexterous Manipulator Teleoperation

The use of hand pose for dexterous manipulator teleoperation is an attractive method to the control of the multi-fingered manipulators. Furthermore, the advancement of the deep learning and depth sensors has encouraged the development of the 3D hand pose estimation. However, developing a 3D hand pose estimation method with an accurate and real-time performance is still a difficult task in computer vision. In this paper, a lightweight depth-based network named biomechanical structure information cascade network (BaSICNet) is proposed by considering the global and local structure of human hands to improve the performance through a cascade network and a bone-constraint loss function. In addition, the BaSICNet is applied to a five-fingered dexterous manipulator platform to achieve visual hand-based teleoperation. Extensive evaluations on two public datasets show that the BaSICNet can produce accurate and fast 3D hand poses (9.15mm and 7.59mm mean errors on NYU and MSRA datasets with 114.7 fps), and can achieve superior 3D hand pose estimation balance of accuracy and speed when compared with state-of-the-art (SOAT) methods. Experiment results on the dexterous manipulator platform also show that the BaSICNet can be applied well for teleoperation.

Monocular 3D Hand Mesh Recovery via Dual Noise Estimation

Current parametric models have made notable progress in 3D hand pose and shape estimation. However, due to the fixed hand topology and complex hand poses, current models are hard to generate meshes that are aligned with the image well. To tackle this issue, we introduce a dual noise estimation method in this paper. Given a single-view image as input, we first adopt a baseline parametric regressor to obtain the coarse hand meshes. We assume the mesh vertices and their image-plane projections are noisy, and can be associated in a unified probabilistic model. We then learn the distributions of noise to refine mesh vertices and their projections. The refined vertices are further utilized to refine camera parameters in a closed-form manner. Consequently, our method obtains well-aligned and high-quality 3D hand meshes. Extensive experiments on the large-scale Interhand2.6M dataset demonstrate that the proposed method not only improves the performance of its baseline by more than 10% but also achieves state-of-the-art performance. Project page: https://github.com/hanhuili/DNE4Hand.

Cross-Constrained Progressive Inference for 3D Hand Pose Estimation with Dynamic Observer-Decision-Adjuster Networks

Generalization is very important for pose estimation, especially for 3D pose estimation where small changes in the 2D images could trigger structural changes in the 3D space. To achieve generalization, the system needs to have the capability of detecting estimation errors by double-checking the projection coherence between the 3D and 2D spaces and adapting its network inference process based on this feedback. Current pose estimation is one-time feed-forward and lacks the capability to gather feedback and adapt the inference outcome. To address this problem, we propose to explore the concept of progressive inference where the network learns an observer to continuously detect the prediction error based on constraints matching, as well as an adjuster to refine its inference outcome based on these constraints errors. Within the context of 3D hand pose estimation, we find that this observer-adjuster design is relatively unstable since the observer is operating in the 2D image domain while the adjuster is operating in the 3D domain. To address this issue, we propose to construct two sets of observers-adjusters with complementary constraints from different perspectives. They operate in a dynamic sequential manner controlled by a decision network to progressively improve the 3D pose estimation. We refer to this method as Cross-Constrained Progressive Inference (CCPI). Our extensive experimental results on FreiHAND and HO-3D benchmark datasets demonstrate that the proposed CCPI method is able to significantly improve the generalization capability and performance of 3D hand pose estimation.

Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation

Previous 3D hand pose estimation methods primarily rely on a single modality, either RGB or depth, and the comprehensive utilization of the dual modalities has not been extensively explored. RGB and depth data provide complementary information and thus can be fused to enhance the robustness of 3D hand pose estimation. However, there exist two problems for applying existing fusion methods in 3D hand pose estimation: redundancy of dense feature fusion and ambiguity of visual features. First, pixel-wise feature interactions introduce high computational costs and ineffective calculations of invalid pixels. Second, visual features suffer from ambiguity due to color and texture similarities, as well as depth holes and noise caused by frequent hand movements, which interferes with modeling cross-modal correlations. In this paper, we propose Keypoint-Fusion for RGB-D based 3D hand pose estimation, which leverages the unique advantages of dual modalities to mutually eliminate the feature ambiguity, and performs cross-modal feature fusion in a more efficient way. Specifically, we focus cross-modal fusion on sparse yet informative spatial regions (i.e. keypoints). Meanwhile, by explicitly extracting relatively more reliable information as disambiguation evidence, depth modality provides 3D geometric information for RGB feature pixels, and RGB modality complements the precise edge information lost due to the depth noise. Keypoint-Fusion achieves state-of-the-art performance on two challenging hand datasets, significantly decreasing the error compared with previous single-modal methods.

SMR: Spatial-Guided Model-Based Regression for 3D Hand Pose and Mesh Reconstruction

3D hand reconstruction is an important technique for human-computer interaction. Interactive experience depends on the accuracy, efficiency, and robustness of the algorithm. Therefore, in this paper, we first propose a balanced framework called spatial-aware regression (SAR) to achieve precise and fast reconstruction. SAR can bridge convolutional networks and graph-structure networks more effectively than existing frameworks to fully exploit extracted spatial information using a novel spatial-aware initial graph building module. In addition, SAR uses adaptive-GCN to make keypoints interact efficiently and effectively; and regresses 2.5D belief maps to characterize uncertainty. SAR is highly flexible because it can predict an arbitrary number of keypoints and apply pose-guided refinement for coarse to fine regression. To produce more rational results for challenging cases and mitigate 3D label reliance, we also propose a more robust model-based framework called spatial-guided model-based regression (SMR) that is based on SAR. There are two critical designs of SMR: 1) it uses SAR to enhance the features with pose information to help the regression of hand model parameters; and 2) it regresses parameters in a spatially aware manner that is similar to SAR. Experiments demonstrate that the proposed frameworks surpass existing fully-supervised approaches on the FreiHAND, HO-3D, RHD, and STB datasets. Also, the performances of the proposed frameworks under weakly/self-supervised settings outperform other competitors. Meanwhile, the proposed frameworks are accurate and efficient.

A versatile interaction framework for robot programming based on hand gestures and poses

This paper proposes a framework for industrial and collaborative robot programming based on the integration of hand gestures and poses. The framework allows operators to control the robot via both End-Effector (EE) and joint movements and to transfer compound shapes accurately to the robot. Seventeen hand gestures, which cover the position and orientation controls of the robotic EE and other auxiliary operations, are designed according to cognitive psychology. Gestures are classified by a deep neural network, which is pre-trained for two-hand pose estimation and fine-tuned on a custom dataset, achieving a test accuracy of 99%. The index finger’s pointing direction and the hand’s orientation are extracted via 3D hand pose estimation to indicate the robotic EE’s moving direction and orientation, respectively. The number of stretched fingers is detected via two-hand pose estimation to represent decimal digits for selecting robot joints and inputting numbers. Finally, we integrate these three manners seamlessly to form a programming framework. We conducted two interaction experiments. The reaction time of the proposed hand gestures in indicating randomly given instructions is significantly less than that of other gesture sets, such as American Sign Language (ASL). The accuracy of our method in compound shape reconstruction is much better than that of hand movement trajectory-based methods, and the operating time is comparable with that of teach pendants.

Lightweight 3D hand pose estimation by cascading CNNs with reinforcement learning

This paper proposes a novel strategy for lightweight 3D hand pose estimation. The strategy decomposes the estimation process into feature extraction and feature exploitation, where feature extraction performs dimension reduction on the original input and outputs feature vectors. Feature exploitation is further analyzed and considered as a path optimization problem, and reinforcement learning (RL) is proved to be capable of tackling the problem accurately. A framework cascading convolutional neural networks (CNNs) and RL is next introduced to validate the effectiveness of the proposed strategy, where two different backbones are used to extract features, and RL is extended into continuous space to enhance accuracy. Ablation studies and experiments are carried out on NYU and ICVL datasets using the proposed strategy with continuous RL. The results show that the accuracy of continuous RL exceeds discrete RL, and the rapidity and accuracy leads the backbones. Comparative studies show the strategy achieves leading rapidity and accuracy in single-view depth-based methods.

Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey

AbstractIn this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D hand pose estimation has been an important research area owing to its potential to enable various applications, such as video understanding, AR/VR, and robotics. However, the performance of models is tied to the quality and quantity of annotated 3D hand poses. Under the status quo, acquiring such annotated 3D hand poses is challenging, e.g., due to the difficulty of 3D annotation and the presence of occlusion. To reveal this problem, we review the pros and cons of existing annotation methods classified as manual, synthetic-model-based, hand-sensor-based, and computational approaches. Additionally, we examine methods for learning 3D hand poses when annotated data are scarce, including self-supervised pretraining, semi-supervised learning, and domain adaptation. Based on the study of efficient annotation and learning, we further discuss limitations and possible future directions in this field.

MTMVC: Semi-supervised 3D hand pose estimation using multi-task and multi-view consistency

The high performance of state-of-the-art deep learning methods for 3D hand pose estimation heavily depends on a large annotated training set. However, it is difficult and time-consuming to obtain the annotations for 3D hand poses. To leverage unannotated images to reduce the annotation cost, we propose a semi-supervised method based on Multi-Task and Multi-View Consistency (MTMVC) for hand pose estimation. First, we obtain the joints based on heatmap prediction and coordinate regression parallelly and encourage their consistency. Second, we introduce multi-view consistency to encourage the predicted poses to be rotation-invariant. Thirdly, to make the network pay more attention to the hand region, we propose a spatially weighted consistency. Experiments on four public datasets showed that our proposed MTMVC outperformed existing semi-supervised hand pose estimation methods, and by only using half of the annotations, the accuracy of our method was comparable to those of several state-of-the-art fully supervised methods.