{"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/capturing-and-inferring-dense-full-body-human-1","title":"Capturing and Inferring Dense Full-Body Human-Scene Contact","arxiv_id":"2206.09553","date":"2022-06-20","proceeding":"CVPR 2022 1","authors":["Chun-Hao P. Huang","Hongwei Yi","Markus Höschle","Matvey Safroshkin","Tsvetelina Alexiadis","Senya Polikovsky","Daniel Scharstein","Michael J. Black"],"abstract":"Inferring human-scene contact (HSC) is the first step toward understanding how humans interact with their surroundings. While detecting 2D human-object interaction (HOI) and reconstructing 3D human pose and shape (HPS) have enjoyed significant progress, reasoning about 3D human-scene contact from a single image is still challenging. Existing HSC detection methods consider only a few types of predefined contact, often reduce body and scene to a small number of primitives, and even overlook image evidence. To predict human-scene contact from a single image, we address the limitations above from both data and algorithmic perspectives. We capture a new dataset called RICH for \"Real scenes, Interaction, Contact and Humans.\" RICH contains multiview outdoor/indoor video sequences at 4K resolution, ground-truth 3D human bodies captured using markerless motion capture, 3D body scans, and high resolution 3D scene scans. A key feature of RICH is that it also contains accurate vertex-level contact labels on the body. Using RICH, we train a network that predicts dense body-scene contacts from a single RGB image. Our key insight is that regions in contact are always occluded so the network needs the ability to explore the whole image for evidence. We use a transformer to learn such non-local relationships and propose a new Body-Scene contact TRansfOrmer (BSTRO). Very few methods explore 3D contact; those that do focus on the feet only, detect foot contact as a post-processing step, or infer contact from body pose without looking at the scene. To our knowledge, BSTRO is the first method to directly estimate 3D body-scene contact from a single image. We demonstrate that BSTRO significantly outperforms the prior art. The code and dataset are available at https://rich.is.tue.mpg.de.","url_abs":"https://arxiv.org/abs/2206.09553v1","url_pdf":"https://arxiv.org/pdf/2206.09553v1.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":"capturing-and-inferring-dense-full-body-human-1","repo_url":"https://github.com/paulchhuang/bstro","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"capturing-and-inferring-dense-full-body-human-1","repo_url":"https://github.com/paulchhuang/rich_toolkit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"contact-detection","task_name":"Contact Detection"},{"task_slug":"dense-contact-estimation","task_name":"Dense contact estimation"},{"task_slug":"markerless-motion-capture","task_name":"Markerless Motion Capture"},{"task_slug":"monocular-3d-human-pose-estimation","task_name":"Monocular 3D Human Pose Estimation"},{"task_slug":"human-scene-contact-detection","task_name":"human-scene contact detection"}],"methods":[],"datasets_introduced":[{"slug":"rich","name":"RICH","full_name":"Real scenes, Interaction, Contact and Humans"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/contact-detection-on-behave","task":"Contact Detection","dataset":"BEHAVE","model":"BSTRO","rank_in_archive_order":3,"of":4,"metrics":{"Precision":"0.615","Recall":"0.527"},"uses_additional_data":false},{"leaderboard":"/sota/dense-contact-estimation-on-mow","task":"Dense contact estimation","dataset":"MOW","model":"BSTRO","rank_in_archive_order":3,"of":4,"metrics":{"F1-Score":"0.112","Precision":"0.204","Recall":"0.126"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.09553","atlas_url":"https://app.syntology.ai/?focus=2206.09553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09553"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/paulchhuang/bstro","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/paulchhuang/rich_toolkit","reach":{"status":"ok"}}],"summary":{"ran":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":"9711320990f8b3dc","entry":"BSTRO_BodyHSC_Network","repo":"paulchhuang/bstro","repo_kind":"official","path":"metro/modeling/bert/modeling_bstro.py","file_url":"https://github.com/paulchhuang/bstro/blob/HEAD/metro/modeling/bert/modeling_bstro.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9711320990f8b3dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}