{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MU7DNYWHFCE37AWZPQREZ46LAY","short_pith_number":"pith:MU7DNYWH","schema_version":"1.0","canonical_sha256":"653e36e2c72889bf82d97c224cf3cb063fe8bfe447aa0b8d541ba449b832d4f2","source":{"kind":"arxiv","id":"2605.14525","version":1},"attestation_state":"computed","paper":{"title":"From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sparse interleaved multi-view inputs with DenseWarper outperform traditional dense simultaneous multi-view methods for 3D human pose estimation on Human3.6M and MPI-INF-3DHP datasets.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjie Chen, Jiaqing Lyu, Kenglun Chang, Ling Li, Yiyun Chen, Yuyan Wang, Zhidong Deng","submitted_at":"2026-05-14T08:08:29Z","abstract_excerpt":"In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach often overlooks the rich temporal dependencies between adjacent frames. We propose a novel 3D human pose estimation input method: the sparse interleaved input to address this. This method leverages images captured from different camera views at various time points (e.g., View 1 at time $t$ and View 2 at time $t+\\delta$), allowing our model to capture rich spatio"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14525","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:08:29Z","cross_cats_sorted":[],"title_canon_sha256":"e1494838098d05fdbd5bdf362caa9883f3986832264c857e586d71b69aaa14e2","abstract_canon_sha256":"181fb88ca03ace2f19b71cb97d8107090aba5725fce7f71f306ba85b03c0390e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.019859Z","signature_b64":"2ZylfwYYEV6V3kuliCk+q/2qcDLof1o7Negp+zndMoSVOB7JYeH9s5bEovvWDGy7iOU2Z0kMkUAEWap50lf7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"653e36e2c72889bf82d97c224cf3cb063fe8bfe447aa0b8d541ba449b832d4f2","last_reissued_at":"2026-05-17T23:39:06.019287Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.019287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Sparse to Dense: Spatio-Temporal Fusion for Multi-View 3D Human Pose Estimation with DenseWarper","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Sparse interleaved multi-view inputs with DenseWarper outperform traditional dense simultaneous multi-view methods for 3D human pose estimation on Human3.6M and MPI-INF-3DHP datasets.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changjie Chen, Jiaqing Lyu, Kenglun Chang, Ling Li, Yiyun Chen, Yuyan Wang, Zhidong Deng","submitted_at":"2026-05-14T08:08:29Z","abstract_excerpt":"In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach often overlooks the rich temporal dependencies between adjacent frames. We propose a novel 3D human pose estimation input method: the sparse interleaved input to address this. This method leverages images captured from different camera views at various time points (e.g., View 1 at time $t$ and View 2 at time $t+\\delta$), allowing our model to capture rich spatio"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"Results demonstrate that our method, utilizing only sparse interleaved images as input, outperforms traditional dense multi-view input approaches and achieves state-of-the-art performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That temporal offsets in the interleaved views can be reliably bridged by epipolar-geometry-based heatmap exchange without introducing motion-induced errors or losing spatial precision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sparse interleaved multi-view inputs with DenseWarper outperform traditional dense simultaneous multi-view methods for 3D human pose estimation on Human3.6M and MPI-INF-3DHP datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"72ca5f3ae3e2b7360e6fd948e967fb2400e7f45841e727ee2d1711f7d46a47e7"},"source":{"id":"2605.14525","kind":"arxiv","version":1},"verdict":{"id":"295a0bb7-c89e-4fd8-a93b-97a3b0097e28","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:16:19.046838Z","strongest_claim":"Results demonstrate that our method, utilizing only sparse interleaved images as input, outperforms traditional dense multi-view input approaches and achieves state-of-the-art performance.","one_line_summary":"Sparse interleaved multi-view inputs with DenseWarper outperform traditional dense simultaneous multi-view methods for 3D human pose estimation on Human3.6M and MPI-INF-3DHP datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That temporal offsets in the interleaved views can be reliably bridged by epipolar-geometry-based heatmap exchange without introducing motion-induced errors or losing spatial precision.","pith_extraction_headline":""},"references":{"count":211,"sample":[{"doi":"","year":null,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Deep learning , author=. 2016 , publisher=","work_id":"cf0899e0-53ee-4591-aae4-f38fa5ac12ad","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages=","work_id":"ce04984c-d5cc-4eb6-a903-2ccd68015be6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Baumgartner, Tobias and Klatt, Stefanie , booktitle=","work_id":"7ec5ef1e-2224-411f-b656-729ee5409246","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":211,"snapshot_sha256":"ab1c6fa8930c391fa0d617cea6c9a6196aea519d92876762ad0d6182d5cc7d97","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":"2605.14525","created_at":"2026-05-17T23:39:06.019408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14525v1","created_at":"2026-05-17T23:39:06.019408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14525","created_at":"2026-05-17T23:39:06.019408+00:00"},{"alias_kind":"pith_short_12","alias_value":"MU7DNYWHFCE3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MU7DNYWHFCE37AWZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MU7DNYWH","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY","json":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY.json","graph_json":"https://pith.science/api/pith-number/MU7DNYWHFCE37AWZPQREZ46LAY/graph.json","events_json":"https://pith.science/api/pith-number/MU7DNYWHFCE37AWZPQREZ46LAY/events.json","paper":"https://pith.science/paper/MU7DNYWH"},"agent_actions":{"view_html":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY","download_json":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY.json","view_paper":"https://pith.science/paper/MU7DNYWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14525&json=true","fetch_graph":"https://pith.science/api/pith-number/MU7DNYWHFCE37AWZPQREZ46LAY/graph.json","fetch_events":"https://pith.science/api/pith-number/MU7DNYWHFCE37AWZPQREZ46LAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY/action/storage_attestation","attest_author":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY/action/author_attestation","sign_citation":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY/action/citation_signature","submit_replication":"https://pith.science/pith/MU7DNYWHFCE37AWZPQREZ46LAY/action/replication_record"}},"created_at":"2026-05-17T23:39:06.019408+00:00","updated_at":"2026-05-17T23:39:06.019408+00:00"}