mlsanityData to 14 Oct 2026

Monocular 3D Hand Mesh Recovery via Dual Noise Estimation

arXiv 2312.15916 ↗First posted 26 Dec 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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: urlhttps://github.com/hanhuili/DNE4Hand.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 26 Dec 2023.

Builds on

23 of 32 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  5. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 575
  6. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  7. 2020InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 245
  8. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  9. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  10. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  11. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  12. 2022LISA: Learning Implicit Shape and Appearance of Handscited by 63
11 more
  1. 2022AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstructioncited by 59
  2. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 49
  3. 2021Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstructioncited by 44
  4. 2022Hand Avatar: Free-Pose Hand Animation and Rendering from Monocular Videocited by 37
  5. 2023ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstructioncited by 37
  6. 20223D Interacting Hand Pose Estimation by Hand De-occlusion and Removalcited by 36
  7. 2023Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wildcited by 36
  8. 2023Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapescited by 26
  9. 2023A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Imagecited by 15
  10. 2022MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstructioncited by 11
  11. 2023Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstructioncited by 4

Built on by

Not cited yet.