{"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/hi-lassie-high-fidelity-articulated-shape-and","title":"Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble","arxiv_id":"2212.11042","date":"2022-12-21","proceeding":"CVPR 2023 1","authors":["Chun-Han Yao","Wei-Chih Hung","Yuanzhen Li","Michael Rubinstein","Ming-Hsuan Yang","Varun Jampani"],"abstract":"Automatically estimating 3D skeleton, shape, camera viewpoints, and part articulation from sparse in-the-wild image ensembles is a severely under-constrained and challenging problem. Most prior methods rely on large-scale image datasets, dense temporal correspondence, or human annotations like camera pose, 2D keypoints, and shape templates. We propose Hi-LASSIE, which performs 3D articulated reconstruction from only 20-30 online images in the wild without any user-defined shape or skeleton templates. We follow the recent work of LASSIE that tackles a similar problem setting and make two significant advances. First, instead of relying on a manually annotated 3D skeleton, we automatically estimate a class-specific skeleton from the selected reference image. Second, we improve the shape reconstructions with novel instance-specific optimization strategies that allow reconstructions to faithful fit on each instance while preserving the class-specific priors learned across all images. Experiments on in-the-wild image ensembles show that Hi-LASSIE obtains higher fidelity state-of-the-art 3D reconstructions despite requiring minimum user input.","url_abs":"https://arxiv.org/abs/2212.11042v4","url_pdf":"https://arxiv.org/pdf/2212.11042v4.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":"hi-lassie-high-fidelity-articulated-shape-and","repo_url":"https://github.com/google/hi-lassie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.11042","atlas_url":"https://app.syntology.ai/?focus=2212.11042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11042"}},"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/google/hi-lassie","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"listed":{"samples":7,"ran":5,"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":"08eeaeb47623cd45","entry":"attn_cosine_sim","repo":"google/hi-lassie","repo_kind":"listed","path":"networks/extractor.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/networks/extractor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08eeaeb47623cd45"}},{"code_sha256_prefix":"135f37701edf71c1","entry":"bfs","repo":"google/hi-lassie","repo_kind":"listed","path":"main/extract_skeleton.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/main/extract_skeleton.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"135f37701edf71c1"}},{"code_sha256_prefix":"107c3f398275bf2c","entry":"get_max_connected_component","repo":"google/hi-lassie","repo_kind":"listed","path":"main/extract_skeleton.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/main/extract_skeleton.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"107c3f398275bf2c"}},{"code_sha256_prefix":"461ed6e2762e4454","entry":"process_bbox","repo":"google/hi-lassie","repo_kind":"listed","path":"utils/data_utils.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/utils/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"461ed6e2762e4454"}},{"code_sha256_prefix":"17df2c88d2380a00","entry":"sil_loss","repo":"google/hi-lassie","repo_kind":"listed","path":"utils/losses.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17df2c88d2380a00"}},{"code_sha256_prefix":"5be6e9126dc4be51","entry":"find_symmetric_pairs","repo":"google/hi-lassie","repo_kind":"listed","path":"main/extract_skeleton.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/main/extract_skeleton.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5be6e9126dc4be51"}},{"code_sha256_prefix":"7607686657827741","entry":"part_center_loss","repo":"google/hi-lassie","repo_kind":"listed","path":"utils/losses.py","file_url":"https://github.com/google/hi-lassie/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7607686657827741"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}