mlsanityData to 7 Oct 2026

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image

arXiv 1908.09999 ↗First posted 27 Aug 2019cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

For 3D hand and body pose estimation task in depth image, a novel anchor-based approach termed Anchor-to-Joint regression network (A2J) with the end-to-end learning ability is proposed. Within A2J, anchor points able to capture global-local spatial context information are densely set on depth image as local regressors for the joints. They contribute to predict the positions of the joints in ensemble way to enhance generalization ability. The proposed 3D articulated pose estimation paradigm is different from the state-of-the-art encoder-decoder based FCN, 3D CNN and point-set based manners. To discover informative anchor points towards certain joint, anchor proposal procedure is also proposed for A2J. Meanwhile 2D CNN (i.e., ResNet-50) is used as backbone network to drive A2J, without using time-consuming 3D convolutional or deconvolutional layers. The experiments on 3 hand datasets and 2 body datasets verify A2J's superiority. Meanwhile, A2J is of high running speed around 100 FPS on single NVIDIA 1080Ti GPU.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 14; 2024: 12; 2025: 5; 2026: 3.

56 papers.

Sort:

By area:

  1. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 320
  2. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  3. 2021Discrete Cosine Transform Network for Guided Depth Map Super-Resolutioncited by 71
  4. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 58
  5. 2023gSDF: Geometry-Driven Signed Distance Functions for 3D Hand-Object Reconstructioncited by 49
  6. 2022Learning to Imitate Object Interactions from Internet Videoscited by 32
  7. 2021HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Mediacited by 29
  8. 2023Spherical Space Feature Decomposition for Guided Depth Map Super-Resolutioncited by 28
  9. 2024EgoGen: An Egocentric Synthetic Data Generatorcited by 27
  10. 2022Versatile Multi-Modal Pre-Training for Human-Centric Perceptioncited by 26
  11. 2024HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interactioncited by 25
  12. 2021DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoderscited by 23
38 more
  1. 2023Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimationcited by 21
  2. 2022Efficient Annotation and Learning for 3D Hand Pose Estimation: A Surveycited by 17
  3. 2022Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wildcited by 17
  4. 2023A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 15
  5. 2024HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fieldscited by 14
  6. 2022NeuralGrasps: Learning Implicit Representations for Grasps of Multiple Robotic Handscited by 12
  7. 2023LiDAR-HMR: 3D Human Mesh Recovery from LiDARcited by 12
  8. 2024HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloudcited by 12
  9. 2021HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networkscited by 11
  10. 2025HORT: Monocular Hand-held Objects Reconstruction with Transformerscited by 11
  11. 2023LPFormer: LiDAR Pose Estimation Transformer with Multi-Task Networkcited by 9
  12. 2023PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Cloudscited by 9
  13. 2024HandOS: 3D Hand Reconstruction in One Stagecited by 9
  14. 2022The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimationcited by 8
  15. 2022TriHorn-Net: A Model for Accurate Depth-Based 3D Hand Pose Estimationcited by 7
  16. 2025SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-trainingcited by 7
  17. 2021Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimationcited by 6
  18. 2022Efficient Virtual View Selection for 3D Hand Pose Estimationcited by 6
  19. 2023Neural Voting Field for Camera-Space 3D Hand Pose Estimationcited by 6
  20. 2021Domain and View-point Agnostic Hand Action Recognitioncited by 5
  21. 2022Image-free Domain Generalization via CLIP for 3D Hand Pose Estimationcited by 4
  22. 2024ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Imagescited by 4
  23. 2021Heuristic Weakly Supervised 3D Human Pose Estimationcited by 3
  24. 2025QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objectscited by 3
  25. 2022ACRNet: Attention Cube Regression Network for Multi-view Real-time 3D Human Pose Estimation in Telemedicinecited by 2
  26. 2023Multimodal Active Measurement for Human Mesh Recovery in Close Proximitycited by 2
  27. 2023ShapeGraFormer: GraFormer-Based Network for Hand-Object Reconstruction from a Single Depth Mapcited by 2
  28. 2024SPiKE: 3D Human Pose from Point Cloud Sequencescited by 2
  29. 2024V-Hands: Touchscreen-based Hand Tracking for Remote Whiteboard Interactioncited by 2
  30. 2023Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Trainingcited by 1
  31. 2023UltraGlove: Hand Pose Estimation with Mems-Ultrasonic Sensorscited by 1
  32. 2024Two Hands Are Better Than One: Resolving Hand to Hand Intersections via Occupancy Networkscited by 1
  33. 2024HandDAGT: A Denoising Adaptive Graph Transformer for 3D Hand Pose Estimationcited by 1
  34. 2021Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimationcited by 0
  35. 2022Mask2Hand: Learning to Predict the 3D Hand Pose and Shape from Shadowcited by 0
  36. 2023Capsules as viewpoint learners for human pose estimationcited by 0
  37. 20233D Pose Nowcasting: Forecast the Future to Improve the Presentcited by 0
  38. 2024Learning Pixel-wise Continuous Depth Representation via Clustering for Depth Completioncited by 0

50 most cited of 56 All 56 (JSON)