{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:755JSKKYBFXZD5RWPQVI2Q2U7D","short_pith_number":"pith:755JSKKY","schema_version":"1.0","canonical_sha256":"ff7a992958096f91f6367c2a8d4354f8d801a5cc03c2f843c8ce63c3edcbc33d","source":{"kind":"arxiv","id":"2501.16617","version":1},"attestation_state":"computed","paper":{"title":"Predicting 3D representations for Dynamic Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beining Wang, Di Qi, Tong Yang, Wenqiang Zhang, Xiangyu Zhang","submitted_at":"2025-01-28T01:31:15Z","abstract_excerpt":"We present a novel framework for dynamic radiance field prediction given monocular video streams. Unlike previous methods that primarily focus on predicting future frames, our method goes a step further by generating explicit 3D representations of the dynamic scene. The framework builds on two core designs. First, we adopt an ego-centric unbounded triplane to explicitly represent the dynamic physical world. Second, we develop a 4D-aware transformer to aggregate features from monocular videos to update the triplane. Coupling these two designs enables us to train the proposed model with large-sc"},"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":"2501.16617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-28T01:31:15Z","cross_cats_sorted":[],"title_canon_sha256":"1c1aed8a467f69f482278b8c8e74772b5cf2a84535c868e4ace0c6f0e218709c","abstract_canon_sha256":"1a840a83ef1ed0ce3cb798db98a740b49469430ed4a2ef829d4219867d304462"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:15.862566Z","signature_b64":"zUl/nfFczmdb2eQfOVJs8mtK67xPnBmfSNydtHMktBpwEzPUIGA2D+JzA68M0SSRBQg1saQlOrJfjXTYjqzRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff7a992958096f91f6367c2a8d4354f8d801a5cc03c2f843c8ce63c3edcbc33d","last_reissued_at":"2026-07-05T10:06:15.862035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:15.862035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting 3D representations for Dynamic Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beining Wang, Di Qi, Tong Yang, Wenqiang Zhang, Xiangyu Zhang","submitted_at":"2025-01-28T01:31:15Z","abstract_excerpt":"We present a novel framework for dynamic radiance field prediction given monocular video streams. Unlike previous methods that primarily focus on predicting future frames, our method goes a step further by generating explicit 3D representations of the dynamic scene. The framework builds on two core designs. First, we adopt an ego-centric unbounded triplane to explicitly represent the dynamic physical world. Second, we develop a 4D-aware transformer to aggregate features from monocular videos to update the triplane. Coupling these two designs enables us to train the proposed model with large-sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16617","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/2501.16617/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":"2501.16617","created_at":"2026-07-05T10:06:15.862094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16617v1","created_at":"2026-07-05T10:06:15.862094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16617","created_at":"2026-07-05T10:06:15.862094+00:00"},{"alias_kind":"pith_short_12","alias_value":"755JSKKYBFXZ","created_at":"2026-07-05T10:06:15.862094+00:00"},{"alias_kind":"pith_short_16","alias_value":"755JSKKYBFXZD5RW","created_at":"2026-07-05T10:06:15.862094+00:00"},{"alias_kind":"pith_short_8","alias_value":"755JSKKY","created_at":"2026-07-05T10:06:15.862094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30347","citing_title":"FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D","json":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D.json","graph_json":"https://pith.science/api/pith-number/755JSKKYBFXZD5RWPQVI2Q2U7D/graph.json","events_json":"https://pith.science/api/pith-number/755JSKKYBFXZD5RWPQVI2Q2U7D/events.json","paper":"https://pith.science/paper/755JSKKY"},"agent_actions":{"view_html":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D","download_json":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D.json","view_paper":"https://pith.science/paper/755JSKKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16617&json=true","fetch_graph":"https://pith.science/api/pith-number/755JSKKYBFXZD5RWPQVI2Q2U7D/graph.json","fetch_events":"https://pith.science/api/pith-number/755JSKKYBFXZD5RWPQVI2Q2U7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D/action/storage_attestation","attest_author":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D/action/author_attestation","sign_citation":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D/action/citation_signature","submit_replication":"https://pith.science/pith/755JSKKYBFXZD5RWPQVI2Q2U7D/action/replication_record"}},"created_at":"2026-07-05T10:06:15.862094+00:00","updated_at":"2026-07-05T10:06:15.862094+00:00"}