{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YL7KYCKOKVFPT4GDKSCGN3RDCW","short_pith_number":"pith:YL7KYCKO","schema_version":"1.0","canonical_sha256":"c2feac094e554af9f0c3548466ee23159bc578c94d68aae2a4c19d67f29b5732","source":{"kind":"arxiv","id":"2311.14603","version":2},"attestation_state":"computed","paper":{"title":"Animate124: Animating One Image to 4D Dynamic Scene","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Gim Hee Lee, Lanqing Hong, Yuyang Zhao, Zhenguo Li, Zhiwen Yan","submitted_at":"2023-11-24T16:47:05Z","abstract_excerpt":"We introduce Animate124 (Animate-one-image-to-4D), the first work to animate a single in-the-wild image into 3D video through textual motion descriptions, an underexplored problem with significant applications. Our 4D generation leverages an advanced 4D grid dynamic Neural Radiance Field (NeRF) model, optimized in three distinct stages using multiple diffusion priors. Initially, a static model is optimized using the reference image, guided by 2D and 3D diffusion priors, which serves as the initialization for the dynamic NeRF. Subsequently, a video diffusion model is employed to learn the motio"},"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":"2311.14603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-24T16:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"fb0c19370a561234fc1c67035a9ac2c44cbbfcb1ba3ba304cc1a6c1728ef11c7","abstract_canon_sha256":"f24cf1926cae636a5e7285029900ecab6cdec5c6fa7e16fb59f8135bb499af06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:27.205538Z","signature_b64":"ICY5lRls63Nzu7VJ/LeuxOs4gJfFgnUqNACbVe8NLBcJu/DPYFXaa3SgS3yP2DFvWTtE4L+Bgch+iK2VX9KxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2feac094e554af9f0c3548466ee23159bc578c94d68aae2a4c19d67f29b5732","last_reissued_at":"2026-07-05T07:46:27.205162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:27.205162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Animate124: Animating One Image to 4D Dynamic Scene","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enze Xie, Gim Hee Lee, Lanqing Hong, Yuyang Zhao, Zhenguo Li, Zhiwen Yan","submitted_at":"2023-11-24T16:47:05Z","abstract_excerpt":"We introduce Animate124 (Animate-one-image-to-4D), the first work to animate a single in-the-wild image into 3D video through textual motion descriptions, an underexplored problem with significant applications. Our 4D generation leverages an advanced 4D grid dynamic Neural Radiance Field (NeRF) model, optimized in three distinct stages using multiple diffusion priors. Initially, a static model is optimized using the reference image, guided by 2D and 3D diffusion priors, which serves as the initialization for the dynamic NeRF. Subsequently, a video diffusion model is employed to learn the motio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14603","kind":"arxiv","version":2},"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/2311.14603/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":"2311.14603","created_at":"2026-07-05T07:46:27.205216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14603v2","created_at":"2026-07-05T07:46:27.205216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14603","created_at":"2026-07-05T07:46:27.205216+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL7KYCKOKVFP","created_at":"2026-07-05T07:46:27.205216+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL7KYCKOKVFPT4GD","created_at":"2026-07-05T07:46:27.205216+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL7KYCKO","created_at":"2026-07-05T07:46:27.205216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22131","citing_title":"Feed-forward Motion In-betweening for Any 4D","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02516","citing_title":"Alignment Is All You Need For X-to-4D Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30268","citing_title":"PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00285","citing_title":"SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07390","citing_title":"ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21592","citing_title":"Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW","json":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW.json","graph_json":"https://pith.science/api/pith-number/YL7KYCKOKVFPT4GDKSCGN3RDCW/graph.json","events_json":"https://pith.science/api/pith-number/YL7KYCKOKVFPT4GDKSCGN3RDCW/events.json","paper":"https://pith.science/paper/YL7KYCKO"},"agent_actions":{"view_html":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW","download_json":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW.json","view_paper":"https://pith.science/paper/YL7KYCKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14603&json=true","fetch_graph":"https://pith.science/api/pith-number/YL7KYCKOKVFPT4GDKSCGN3RDCW/graph.json","fetch_events":"https://pith.science/api/pith-number/YL7KYCKOKVFPT4GDKSCGN3RDCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW/action/storage_attestation","attest_author":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW/action/author_attestation","sign_citation":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW/action/citation_signature","submit_replication":"https://pith.science/pith/YL7KYCKOKVFPT4GDKSCGN3RDCW/action/replication_record"}},"created_at":"2026-07-05T07:46:27.205216+00:00","updated_at":"2026-07-05T07:46:27.205216+00:00"}