{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KOALJZDO6K4GD2GVZOUWORXVMQ","short_pith_number":"pith:KOALJZDO","schema_version":"1.0","canonical_sha256":"5380b4e46ef2b861e8d5cba96746f56425ba634a7b171f15060e127404094c22","source":{"kind":"arxiv","id":"2501.02158","version":3},"attestation_state":"computed","paper":{"title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Joe Lin, Wayne Wu, Zhizheng Liu","submitted_at":"2025-01-04T01:53:51Z","abstract_excerpt":"Reconstructing human motion and its surrounding environment is crucial for understanding human-scene interaction and predicting human movements in the scene. While much progress has been made in capturing human-scene interaction in constrained environments, those prior methods can hardly reconstruct the natural and diverse human motion and scene context from web videos. In this work, we propose JOSH, a novel optimization-based method for 4D human-scene reconstruction in the wild from monocular videos. JOSH uses techniques in both dense scene reconstruction and human mesh recovery as initializa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.02158","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T01:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"761ee92230fe43c69478e777ed558b0edbd7fa6d73ff423b620424669000f8df","abstract_canon_sha256":"5750bccb51434837c3bd934e459fc358bbd049a8512b220a5df1320c08d1d466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:07.722333Z","signature_b64":"xSlTQfxUeKN85+SFSkHNEXUuXXWafi+hr7RUyHYrBU3DnVOXDS0ZRV4HFl0I6fjqnxoqnJDFJLZMR/f4yhhCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5380b4e46ef2b861e8d5cba96746f56425ba634a7b171f15060e127404094c22","last_reissued_at":"2026-07-01T00:17:07.721812Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:07.721812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Joe Lin, Wayne Wu, Zhizheng Liu","submitted_at":"2025-01-04T01:53:51Z","abstract_excerpt":"Reconstructing human motion and its surrounding environment is crucial for understanding human-scene interaction and predicting human movements in the scene. While much progress has been made in capturing human-scene interaction in constrained environments, those prior methods can hardly reconstruct the natural and diverse human motion and scene context from web videos. In this work, we propose JOSH, a novel optimization-based method for 4D human-scene reconstruction in the wild from monocular videos. JOSH uses techniques in both dense scene reconstruction and human mesh recovery as initializa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02158","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.02158/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.02158","created_at":"2026-07-01T00:17:07.721874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02158v3","created_at":"2026-07-01T00:17:07.721874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02158","created_at":"2026-07-01T00:17:07.721874+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOALJZDO6K4G","created_at":"2026-07-01T00:17:07.721874+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOALJZDO6K4GD2GV","created_at":"2026-07-01T00:17:07.721874+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOALJZDO","created_at":"2026-07-01T00:17:07.721874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.02350","citing_title":"TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26879","citing_title":"Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17014","citing_title":"RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19624","citing_title":"GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ","json":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ.json","graph_json":"https://pith.science/api/pith-number/KOALJZDO6K4GD2GVZOUWORXVMQ/graph.json","events_json":"https://pith.science/api/pith-number/KOALJZDO6K4GD2GVZOUWORXVMQ/events.json","paper":"https://pith.science/paper/KOALJZDO"},"agent_actions":{"view_html":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ","download_json":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ.json","view_paper":"https://pith.science/paper/KOALJZDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02158&json=true","fetch_graph":"https://pith.science/api/pith-number/KOALJZDO6K4GD2GVZOUWORXVMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KOALJZDO6K4GD2GVZOUWORXVMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ/action/storage_attestation","attest_author":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ/action/author_attestation","sign_citation":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ/action/citation_signature","submit_replication":"https://pith.science/pith/KOALJZDO6K4GD2GVZOUWORXVMQ/action/replication_record"}},"created_at":"2026-07-01T00:17:07.721874+00:00","updated_at":"2026-07-01T00:17:07.721874+00:00"}