# From 2D Alignment to 3D Plausibility: Unifying Heterogeneous 2D Priors and Penetration-Free Diffusion for Occlusion-Robust Two-Hand Reconstruction

arXiv: https://arxiv.org/abs/2503.17788 · HTML: https://mlsanity.com/paper/2503.17788/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 22 Mar 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion](https://mlsanity.com/paper/2312.07531/) (2023)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [End-to-end Hand Mesh Recovery from a Monocular RGB Image](https://mlsanity.com/paper/1902.09305/) (2019)
- [Capturing Hands in Action using Discriminative Salient Points and Physics Simulation](https://mlsanity.com/paper/1506.02178/) (2015)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [Interacting Attention Graph for Single Image Two-Hand Reconstruction](https://mlsanity.com/paper/2203.09364/) (2022)
- [Generative Proxemics: A Prior for 3D Social Interaction from Images](https://mlsanity.com/paper/2306.09337/) (2023)
- [ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction](https://mlsanity.com/paper/2303.05938/) (2023)
- [Bringing Inputs to Shared Domains for 3D Interacting Hands Recovery in the Wild](https://mlsanity.com/paper/2303.13652/) (2023)
- [A Dataset of Relighted 3D Interacting Hands](https://mlsanity.com/paper/2310.17768/) (2023)
- [A Probabilistic Attention Model with Occlusion-aware Texture Regression for 3D Hand Reconstruction from a Single RGB Image](https://mlsanity.com/paper/2304.14299/) (2023)
- [InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion](https://mlsanity.com/paper/2403.17422/) (2024)
- [A Simple Baseline for Efficient Hand Mesh Reconstruction](https://mlsanity.com/paper/2403.01813/) (2024)
- [ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model](https://mlsanity.com/paper/2410.07296/) (2024)
- [Reconstructing Interacting Hands with Interaction Prior from Monocular Images](https://mlsanity.com/paper/2308.14082/) (2023)
- [HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback](https://mlsanity.com/paper/2312.12227/) (2023)
- [Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios](https://mlsanity.com/paper/2410.20359/) (2024)

## Abstract (arXiv)

Two-hand reconstruction from monocular images is hampered by complex poses and severe occlusions, which often cause interaction misalignment and two-hand penetration. We address this by decoupling the problem into 2D structural alignment and 3D spatial interaction alignment, each handled by a tailored component. For 2D alignment, we pioneer the attempt to unify heterogeneous structural priors (keypoints, segmentation, and depth) from vision foundation models as complementary structured guidance for two-hand recovery. Instead of extracting priors prediction as explicit inputs, we propose a fusion-alignment encoder that absorbs their structural knowledge implicitly, achieving foundation-level guidance without foundation-level cost. For 3D spatial alignment, we propose a two-hand penetration-free diffusion model that learns a generative mapping from interpenetrated poses to realistic, collision-free configurations. Guided by collision gradients during denoising, the model converges toward the manifold of valid two-hand interactions, preserving geometric and kinematic coherence. This generative formulation approach enables physically credible reconstructions even under occlusion or ambiguous visual input. Extensive experiments on InterHand2.6M and HIC show state-of-the-art or leading performance in interaction alignment and penetration suppression. Project: https://gaogehan.github.io/A2P/