{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simhand-mining-similar-hands-for-large-scale","title":"SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training","arxiv_id":"2502.15251","date":"2025-02-21","proceeding":null,"authors":["Nie Lin","Takehiko Ohkawa","Yifei HUANG","Mingfang Zhang","Minjie Cai","Ming Li","Ryosuke Furuta","Yoichi Sato"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2502.15251v3","url_pdf":"https://arxiv.org/pdf/2502.15251v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simhand-mining-similar-hands-for-large-scale","repo_url":"https://github.com/ut-vision/simhand","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.15251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15251"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/ut-vision/SiMHand","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ut-vision/simhand","reach":{"status":"ok"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"600df819ea3f132b","entry":"calculate_epe_statistics","repo":"ut-vision/SiMHand","repo_kind":"official","path":"src/experiments/evaluation_utils.py","file_url":"https://github.com/ut-vision/SiMHand/blob/HEAD/src/experiments/evaluation_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"600df819ea3f132b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}