{"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"}