mlsanityData to 14 Oct 2026

Learning Transformation-Isomorphic Latent Space for Accurate Hand Pose Estimation

arXiv 2502.12535 ↗First posted 18 Feb 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Vision-based regression tasks, such as hand pose estimation, have achieved higher accuracy and faster convergence through representation learning. However, existing representation learning methods often encounter the following issues: the high semantic level of features extracted from images is inadequate for regressing low-level information, and the extracted features include task-irrelevant information, reducing their compactness and interfering with regression tasks. To address these challenges, we propose TI-Net, a highly versatile visual Network backbone designed to construct a Transformation Isomorphic latent space. Specifically, we employ linear transformations to model geometric transformations in the latent space and ensure that rm TI-Net aligns them with those in the image space. This ensures that the latent features capture compact, low-level information beneficial for pose estimation tasks. We evaluated TI-Net on the hand pose estimation task to demonstrate the network's superiority. On the DexYCB dataset, TI-Net achieved a 10% improvement in the PA-MPJPE metric compared to specialized state-of-the-art (SOTA) hand pose estimation methods. Our code will be released in the future.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 58 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

45 of 58 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  7. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  8. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  9. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  10. 2020A Survey on Contrastive Self-supervised Learningcited by 554
  11. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  12. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
33 more
  1. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 456
  2. 2017Learning from Synthetic Humanscited by 359
  3. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  4. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  5. 2023Reconstructing Hands in 3D with Transformerscited by 306
  6. 2020Understanding Human Hands in Contact at Internet Scalecited by 281
  7. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  8. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 141
  9. 2019End-to-end Hand Mesh Recovery from a Monocular RGB Imagecited by 124
  10. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 123
  11. 2020Epipolar Transformerscited by 117
  12. 2022Revealing the Dark Secrets of Masked Image Modelingcited by 117
  13. 2022HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Networkcited by 96
  14. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  15. 2021Weakly Supervised Contrastive Learningcited by 81
  16. 2022P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimationcited by 80
  17. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  18. 2023Masked Image Modeling with Local Multi-Scale Reconstructioncited by 43
  19. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  20. 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
  21. 2023Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wildcited by 36
  22. 2022Contrastive Positive Mining for Unsupervised 3D Action Representation Learningcited by 34
  23. 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 34
  24. 2022Consistent 3D Hand Reconstruction in Video via self-supervised Learningcited by 28
  25. 2024A Simple Baseline for Efficient Hand Mesh Reconstructioncited by 27
  26. 2023Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimationcited by 21
  27. 2024RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learningcited by 15
  28. 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyondcited by 13
  29. 2023Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfoldingcited by 10
  30. 2023HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learningcited by 7
  31. 2023Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimationcited by 7
  32. 2021PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learningcited by 2
  33. 2024Pre-Training for 3D Hand Pose Estimation with Contrastive Learning on Large-Scale Hand Images in the Wildcited by 2

Built on by

Not cited yet.