# SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training

arXiv: https://arxiv.org/abs/2502.15251 · HTML: https://mlsanity.com/paper/2502.15251/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 21 Feb 2025.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [Large Batch Training of Convolutional Networks](https://mlsanity.com/paper/1708.03888/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities](https://mlsanity.com/paper/2203.14712/) (2022)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [3D Hand Shape and Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1903.00812/) (2019)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time](https://mlsanity.com/paper/2106.05266/) (2021)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data](https://mlsanity.com/paper/2003.09572/) (2020)
- [Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints](https://mlsanity.com/paper/2003.09282/) (2020)
- [HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network](https://mlsanity.com/paper/2203.14564/) (2022)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Model-based 3D Hand Reconstruction via Self-Supervised Learning](https://mlsanity.com/paper/2103.11703/) (2021)
- [AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation](https://mlsanity.com/paper/2304.12301/) (2023)

## Built on by (most cited first, 7 of 7)

- [MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation](https://mlsanity.com/paper/2505.16602/) (2025)
- [Towards Egocentric 3D Hand Pose Estimation in Unseen Domains](https://mlsanity.com/paper/2601.06537/) (2026)
- [SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation](https://mlsanity.com/paper/2608.04196/) (2026)
- [Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance](https://mlsanity.com/paper/2505.14346/) (2025)
- [EgoBrain: Synergizing Minds and Eyes For Human Action Understanding](https://mlsanity.com/paper/2506.01353/) (2025)
- [Generative Modeling of Shape-Dependent Self-Contact Human Poses](https://mlsanity.com/paper/2509.23393/) (2025)
- [Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting](https://mlsanity.com/paper/2607.15890/) (2026)

## Abstract (arXiv)

We present a framework for pre-training of 3D hand pose estimation from in-the-wild hand images sharing with similar hand characteristics, dubbed SimHand. Pre-training with large-scale images achieves promising results in various tasks, but prior methods for 3D hand pose pre-training have not fully utilized the potential of diverse hand images accessible from in-the-wild videos. To facilitate scalable pre-training, we first prepare an extensive pool of hand images from in-the-wild videos and design our pre-training method with contrastive learning. Specifically, we collect over 2.0M hand images from recent human-centric videos, such as 100DOH and Ego4D. To extract discriminative information from these images, we focus on the similarity of hands: pairs of non-identical samples with similar hand poses. We then propose a novel contrastive learning method that embeds similar hand pairs closer in the feature space. Our method not only learns from similar samples but also adaptively weights the contrastive learning loss based on inter-sample distance, leading to additional performance gains. Our experiments demonstrate that our method outperforms conventional contrastive learning approaches that produce positive pairs sorely from a single image with data augmentation. We achieve significant improvements over the state-of-the-art method (PeCLR) in various datasets, with gains of 15% on FreiHand, 10% on DexYCB, and 4% on AssemblyHands. Our code is available at https://github.com/ut-vision/SiMHand.