{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JL3MZLUWWK35WGGFAM7LQ2NGUO","short_pith_number":"pith:JL3MZLUW","schema_version":"1.0","canonical_sha256":"4af6ccae96b2b7db18c5033eb869a6a3a5120340f86d0566645c8c0f6d556330","source":{"kind":"arxiv","id":"2503.20785","version":1},"attestation_state":"computed","paper":{"title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Wang, Huiqiang Sun, Liao Shen, Shoukang Hu, Tianqi Liu, Wei Li, Zhaoxi Chen, Zhiguo Cao, Zihao Huang, Ziwei Liu","submitted_at":"2025-03-26T17:59:44Z","abstract_excerpt":"We present Free4D, a novel tuning-free framework for 4D scene generation from a single image. Existing methods either focus on object-level generation, making scene-level generation infeasible, or rely on large-scale multi-view video datasets for expensive training, with limited generalization ability due to the scarcity of 4D scene data. In contrast, our key insight is to distill pre-trained foundation models for consistent 4D scene representation, which offers promising advantages such as efficiency and generalizability. 1) To achieve this, we first animate the input image using image-to-vid"},"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":"2503.20785","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T17:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"2dfa89438f0cebfc9e924af392921f03335dd1ebf0138bda3d8611bc0a751225","abstract_canon_sha256":"91d04c04da7b281fb9323df84b0c1e2612d9b3579ea131ab2506d2f0a15f58ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:44.187419Z","signature_b64":"gxvn9j7Lj0rvqpdr8xYe3YOIiVQ0pgyFzYUbjGOUtEwhLRpmndPfINtGM2CHjUYItF63TEePVF3w0XmEX7SnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4af6ccae96b2b7db18c5033eb869a6a3a5120340f86d0566645c8c0f6d556330","last_reissued_at":"2026-07-05T10:39:44.186922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:44.186922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangcong Wang, Huiqiang Sun, Liao Shen, Shoukang Hu, Tianqi Liu, Wei Li, Zhaoxi Chen, Zhiguo Cao, Zihao Huang, Ziwei Liu","submitted_at":"2025-03-26T17:59:44Z","abstract_excerpt":"We present Free4D, a novel tuning-free framework for 4D scene generation from a single image. Existing methods either focus on object-level generation, making scene-level generation infeasible, or rely on large-scale multi-view video datasets for expensive training, with limited generalization ability due to the scarcity of 4D scene data. In contrast, our key insight is to distill pre-trained foundation models for consistent 4D scene representation, which offers promising advantages such as efficiency and generalizability. 1) To achieve this, we first animate the input image using image-to-vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20785","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/2503.20785/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":"2503.20785","created_at":"2026-07-05T10:39:44.186983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20785v1","created_at":"2026-07-05T10:39:44.186983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20785","created_at":"2026-07-05T10:39:44.186983+00:00"},{"alias_kind":"pith_short_12","alias_value":"JL3MZLUWWK35","created_at":"2026-07-05T10:39:44.186983+00:00"},{"alias_kind":"pith_short_16","alias_value":"JL3MZLUWWK35WGGF","created_at":"2026-07-05T10:39:44.186983+00:00"},{"alias_kind":"pith_short_8","alias_value":"JL3MZLUW","created_at":"2026-07-05T10:39:44.186983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23105","citing_title":"Compression and Retrieval: Implicit Memory Retrieval for Video World Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO","json":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO.json","graph_json":"https://pith.science/api/pith-number/JL3MZLUWWK35WGGFAM7LQ2NGUO/graph.json","events_json":"https://pith.science/api/pith-number/JL3MZLUWWK35WGGFAM7LQ2NGUO/events.json","paper":"https://pith.science/paper/JL3MZLUW"},"agent_actions":{"view_html":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO","download_json":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO.json","view_paper":"https://pith.science/paper/JL3MZLUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20785&json=true","fetch_graph":"https://pith.science/api/pith-number/JL3MZLUWWK35WGGFAM7LQ2NGUO/graph.json","fetch_events":"https://pith.science/api/pith-number/JL3MZLUWWK35WGGFAM7LQ2NGUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO/action/storage_attestation","attest_author":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO/action/author_attestation","sign_citation":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO/action/citation_signature","submit_replication":"https://pith.science/pith/JL3MZLUWWK35WGGFAM7LQ2NGUO/action/replication_record"}},"created_at":"2026-07-05T10:39:44.186983+00:00","updated_at":"2026-07-05T10:39:44.186983+00:00"}