{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZG63N5RUVFBT4IQ76L7HSZM232","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4ef1e44f308a1b30347c8c2ea073e4cbf7097eba2088aef40cf926fee55d7b04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T18:00:07Z","title_canon_sha256":"e10ca177b04eace8e788f2d234d9e873feb9c044caa4273ffd3087e0f4ca24ad"},"schema_version":"1.0","source":{"id":"2410.03825","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03825","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03825v2","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03825","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZG63N5RUVFBT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZG63N5RUVFBT4IQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZG63N5RU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ccd3f9f69f0caddba52143bd87d27a5de27765ce964f25f3800bc0868faf168d","target":"graph","created_at":"2026-05-17T23:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics, even without an explicit motion representation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Suitable dynamic posed videos with depth labels exist in sufficient quantity and quality to allow fine-tuning to generalize to arbitrary motion and deformation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A pointmap estimator fine-tuned on limited dynamic video data can estimate geometry in moving scenes without explicit motion modeling."}],"snapshot_sha256":"7cc5b618e5ab3b0499c32f868a933f5d546ae2adf40daaa35cfd5ae0a16015ec"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9b8a0dba0acbc64f0ac1ce52181a5ee36208037b2ca1c01e23840bc164be249c"},"paper":{"abstract_excerpt":"Estimating geometry from dynamic scenes, where objects move and deform over time, remains a core challenge in computer vision. Current approaches often rely on multi-stage pipelines or global optimizations that decompose the problem into subtasks, like depth and flow, leading to complex systems prone to errors. In this paper, we present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. Our key insight is that by simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously o","authors_text":"Charles Herrmann, Deqing Sun, Forrester Cole, Junhwa Hur, Junyi Zhang, Ming-Hsuan Yang, Trevor Darrell, Varun Jampani","cross_cats":[],"headline":"A pointmap estimator fine-tuned on limited dynamic video data can estimate geometry in moving scenes without explicit motion modeling.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T18:00:07Z","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"},"references":{"count":169,"internal_anchors":3,"resolved_work":169,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Deep learning , author=. 2016 , publisher=","work_id":"cf0899e0-53ee-4591-aae4-f38fa5ac12ad","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Repurposing diffusion-based image generators for monocular depth estimation , author=","work_id":"5161405f-a02d-444d-b9c8-5673b4c5d9bc","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Wang, Wenshan and Hu, Yaoyu and Scherer, Sebastian , booktitle=CoRL, pages=. Tartan","work_id":"b8109ebf-41b7-472b-81bc-337d4d69facd","year":null}],"snapshot_sha256":"01953506d9b3e2115280417af4393463ee2ac28f24b7c8388828a4e815a02cd6"},"source":{"id":"2410.03825","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T14:36:24.653161Z","id":"55b4dfb0-921a-4c88-b11d-a004d94f9b98","model_set":{"reader":"grok-4.3"},"one_line_summary":"By fine-tuning DUST3R to output per-timestep pointmaps on scarce dynamic video datasets, MonST3R achieves stronger video depth and pose estimation without explicit motion modeling.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A pointmap estimator fine-tuned on limited dynamic video data can estimate geometry in moving scenes without explicit motion modeling.","strongest_claim":"By posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics, even without an explicit motion representation.","weakest_assumption":"Suitable dynamic posed videos with depth labels exist in sufficient quantity and quality to allow fine-tuning to generalize to arbitrary motion and deformation."}},"verdict_id":"55b4dfb0-921a-4c88-b11d-a004d94f9b98"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8374a3f1894ad320b953df7c59de76d9e56970335a2c6d73bc5bf8fbdc2f8833","target":"record","created_at":"2026-05-17T23:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4ef1e44f308a1b30347c8c2ea073e4cbf7097eba2088aef40cf926fee55d7b04","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T18:00:07Z","title_canon_sha256":"e10ca177b04eace8e788f2d234d9e873feb9c044caa4273ffd3087e0f4ca24ad"},"schema_version":"1.0","source":{"id":"2410.03825","kind":"arxiv","version":2}},"canonical_sha256":"c9bdb6f634a9433e221ff2fe79659ade9ead405d984801be53420d1c22b86162","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9bdb6f634a9433e221ff2fe79659ade9ead405d984801be53420d1c22b86162","first_computed_at":"2026-05-17T23:38:52.330843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.330843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9y1O9VFRMTTJ3FsrHvz1Zds/inbmtpvuE1P1G9pvzEJfvDhM3GULiQT8jOcpdGCBcac/gEPk8UucfgGlrEqbAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.331270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03825","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8374a3f1894ad320b953df7c59de76d9e56970335a2c6d73bc5bf8fbdc2f8833","sha256:ccd3f9f69f0caddba52143bd87d27a5de27765ce964f25f3800bc0868faf168d"],"state_sha256":"b91b79c6213d5f20761a1cdbb98a095f8f35a8daf10de6abad324f8298ee5e7a"}