{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AGDIUM2MHYZLPDCG2VIW5QQFC2","short_pith_number":"pith:AGDIUM2M","schema_version":"1.0","canonical_sha256":"01868a334c3e32b78c46d5516ec20516a5c6efa8dce794972903a0e8c681deab","source":{"kind":"arxiv","id":"2505.24521","version":1},"attestation_state":"computed","paper":{"title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaojuan Qi, Xin Yu, Yang-Tian Sun, Yan-Pei Cao, Yi-Hua Huang, Yuan-Chen Guo, Zehuan Huang, Ziyi Yang","submitted_at":"2025-05-30T12:31:59Z","abstract_excerpt":"Recently, methods leveraging diffusion model priors to assist monocular geometric estimation (e.g., depth and normal) have gained significant attention due to their strong generalization ability. However, most existing works focus on estimating geometric properties within the camera coordinate system of individual video frames, neglecting the inherent ability of diffusion models to determine inter-frame correspondence. In this work, we demonstrate that, through appropriate design and fine-tuning, the intrinsic consistency of video generation models can be effectively harnessed for consistent g"},"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":"2505.24521","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:31:59Z","cross_cats_sorted":[],"title_canon_sha256":"88a49fc7636c3a5467cd029ebf94df9e5ca1e5665764cc63b339031c19abfcf0","abstract_canon_sha256":"0fcea39148a8a0729540976ebf20e4f10399ad78f32dd7a20a572f8ff3219d56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:51.663808Z","signature_b64":"1c3ogoRTL4NePX3/4m1B7iFOr/uuSLYLaIGKWAnAPD4iShyftUs45nYtybp3zm3g8vv12mTuODtSe0d135EfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01868a334c3e32b78c46d5516ec20516a5c6efa8dce794972903a0e8c681deab","last_reissued_at":"2026-07-05T11:12:51.663297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:51.663297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaojuan Qi, Xin Yu, Yang-Tian Sun, Yan-Pei Cao, Yi-Hua Huang, Yuan-Chen Guo, Zehuan Huang, Ziyi Yang","submitted_at":"2025-05-30T12:31:59Z","abstract_excerpt":"Recently, methods leveraging diffusion model priors to assist monocular geometric estimation (e.g., depth and normal) have gained significant attention due to their strong generalization ability. However, most existing works focus on estimating geometric properties within the camera coordinate system of individual video frames, neglecting the inherent ability of diffusion models to determine inter-frame correspondence. In this work, we demonstrate that, through appropriate design and fine-tuning, the intrinsic consistency of video generation models can be effectively harnessed for consistent g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24521","kind":"arxiv","version":1},"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/2505.24521/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":"2505.24521","created_at":"2026-07-05T11:12:51.663374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24521v1","created_at":"2026-07-05T11:12:51.663374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24521","created_at":"2026-07-05T11:12:51.663374+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGDIUM2MHYZL","created_at":"2026-07-05T11:12:51.663374+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGDIUM2MHYZLPDCG","created_at":"2026-07-05T11:12:51.663374+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGDIUM2M","created_at":"2026-07-05T11:12:51.663374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25308","citing_title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2","json":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2.json","graph_json":"https://pith.science/api/pith-number/AGDIUM2MHYZLPDCG2VIW5QQFC2/graph.json","events_json":"https://pith.science/api/pith-number/AGDIUM2MHYZLPDCG2VIW5QQFC2/events.json","paper":"https://pith.science/paper/AGDIUM2M"},"agent_actions":{"view_html":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2","download_json":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2.json","view_paper":"https://pith.science/paper/AGDIUM2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24521&json=true","fetch_graph":"https://pith.science/api/pith-number/AGDIUM2MHYZLPDCG2VIW5QQFC2/graph.json","fetch_events":"https://pith.science/api/pith-number/AGDIUM2MHYZLPDCG2VIW5QQFC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2/action/storage_attestation","attest_author":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2/action/author_attestation","sign_citation":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2/action/citation_signature","submit_replication":"https://pith.science/pith/AGDIUM2MHYZLPDCG2VIW5QQFC2/action/replication_record"}},"created_at":"2026-07-05T11:12:51.663374+00:00","updated_at":"2026-07-05T11:12:51.663374+00:00"}