{"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/snarf-differentiable-forward-skinning-for","title":"SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes","arxiv_id":"2104.03953","date":"2021-04-08","proceeding":"ICCV 2021 10","authors":["Xu Chen","Yufeng Zheng","Michael J. Black","Otmar Hilliges","Andreas Geiger"],"abstract":"Neural implicit surface representations have emerged as a promising paradigm to capture 3D shapes in a continuous and resolution-independent manner. However, adapting them to articulated shapes is non-trivial. Existing approaches learn a backward warp field that maps deformed to canonical points. However, this is problematic since the backward warp field is pose dependent and thus requires large amounts of data to learn. To address this, we introduce SNARF, which combines the advantages of linear blend skinning (LBS) for polygonal meshes with those of neural implicit surfaces by learning a forward deformation field without direct supervision. This deformation field is defined in canonical, pose-independent space, allowing for generalization to unseen poses. Learning the deformation field from posed meshes alone is challenging since the correspondences of deformed points are defined implicitly and may not be unique under changes of topology. We propose a forward skinning model that finds all canonical correspondences of any deformed point using iterative root finding. We derive analytical gradients via implicit differentiation, enabling end-to-end training from 3D meshes with bone transformations. Compared to state-of-the-art neural implicit representations, our approach generalizes better to unseen poses while preserving accuracy. We demonstrate our method in challenging scenarios on (clothed) 3D humans in diverse and unseen poses.","url_abs":"https://arxiv.org/abs/2104.03953v3","url_pdf":"https://arxiv.org/pdf/2104.03953v3.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":"snarf-differentiable-forward-skinning-for","repo_url":"https://github.com/xuchen-ethz/SNARF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-human-reconstruction","task_name":"3D Human Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-reconstruction-on-4d-dress","task":"3D Human Reconstruction","dataset":"4D-DRESS","model":"SNARF_Inner","rank_in_archive_order":3,"of":22,"metrics":{"Chamfer (cm)":"1.158","IoU":"0.907","Normal Consistency":"0.843"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-reconstruction-on-4d-dress","task":"3D Human Reconstruction","dataset":"4D-DRESS","model":"SNARF_Outer","rank_in_archive_order":6,"of":22,"metrics":{"Chamfer (cm)":"1.248","IoU":"0.930","Normal Consistency":"0.827"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03953"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuchen-ethz/SNARF","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/xuchen-ethz/snarf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"43ebe3b786b2d59b","entry":"to_np","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"preprocess/body_model.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/preprocess/body_model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43ebe3b786b2d59b"}},{"code_sha256_prefix":"94904a5bd2e1074f","entry":"to_tensor","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"preprocess/body_model.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/preprocess/body_model.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94904a5bd2e1074f"}},{"code_sha256_prefix":"876e716af6ec6e34","entry":"broyden","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/broyden.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/broyden.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"876e716af6ec6e34"}},{"code_sha256_prefix":"74929499f390a6b9","entry":"calculate_iou","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/metrics.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74929499f390a6b9"}},{"code_sha256_prefix":"40caf9fbfe050a14","entry":"get_embedder","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/network.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/network.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40caf9fbfe050a14"}},{"code_sha256_prefix":"a277c1c958d7611b","entry":"hierarchical_softmax","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/helpers.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a277c1c958d7611b"}},{"code_sha256_prefix":"1a68f2ff6472e1fc","entry":"masked_softmax","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/helpers.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a68f2ff6472e1fc"}},{"code_sha256_prefix":"6883b22def79a831","entry":"rectify_pose","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/helpers.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6883b22def79a831"}},{"code_sha256_prefix":"6018c352d472bd22","entry":"skinning","repo":"xuchen-ethz/SNARF","repo_kind":"official","path":"lib/model/deformer.py","file_url":"https://github.com/xuchen-ethz/SNARF/blob/HEAD/lib/model/deformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6018c352d472bd22"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}