{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TQSYSDK2XABNIACRGG2KXN3CL6","short_pith_number":"pith:TQSYSDK2","schema_version":"1.0","canonical_sha256":"9c25890d5ab802d4005131b4abb7625f9e1286dc6294f0b7ac099491f2f86de6","source":{"kind":"arxiv","id":"2412.09597","version":1},"attestation_state":"computed","paper":{"title":"LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chen Yang, Hongkai Xiong, Jiemin Fang, Lingxi Xie, Qi Tian, Wei Shen, Wenrui Dai, Xiaopeng Zhang, Yabo Chen","submitted_at":"2024-12-12T18:58:42Z","abstract_excerpt":"Single-image 3D reconstruction remains a fundamental challenge in computer vision due to inherent geometric ambiguities and limited viewpoint information. Recent advances in Latent Video Diffusion Models (LVDMs) offer promising 3D priors learned from large-scale video data. However, leveraging these priors effectively faces three key challenges: (1) degradation in quality across large camera motions, (2) difficulties in achieving precise camera control, and (3) geometric distortions inherent to the diffusion process that damage 3D consistency. We address these challenges by proposing LiftImage"},"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":"2412.09597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:58:42Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"cd16d21d7f63104f2b7c4ed5b2e31151e02d5a27df538914efcb431eee979649","abstract_canon_sha256":"57fe6856c480afd3d28b44959595bdbbd243ec90e39cf96310135f149fa5071d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:26.918488Z","signature_b64":"3BbplPVHbRxi/LDZAvdJBOlYgJvKyHLILLeeu+7pwsx0OD19Tu0v/UvKkoV1NamIf+Xcie9aCZRV57AXwtVcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c25890d5ab802d4005131b4abb7625f9e1286dc6294f0b7ac099491f2f86de6","last_reissued_at":"2026-07-05T09:48:26.917921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:26.917921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chen Yang, Hongkai Xiong, Jiemin Fang, Lingxi Xie, Qi Tian, Wei Shen, Wenrui Dai, Xiaopeng Zhang, Yabo Chen","submitted_at":"2024-12-12T18:58:42Z","abstract_excerpt":"Single-image 3D reconstruction remains a fundamental challenge in computer vision due to inherent geometric ambiguities and limited viewpoint information. Recent advances in Latent Video Diffusion Models (LVDMs) offer promising 3D priors learned from large-scale video data. However, leveraging these priors effectively faces three key challenges: (1) degradation in quality across large camera motions, (2) difficulties in achieving precise camera control, and (3) geometric distortions inherent to the diffusion process that damage 3D consistency. We address these challenges by proposing LiftImage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09597","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/2412.09597/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":"2412.09597","created_at":"2026-07-05T09:48:26.917983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09597v1","created_at":"2026-07-05T09:48:26.917983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09597","created_at":"2026-07-05T09:48:26.917983+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQSYSDK2XABN","created_at":"2026-07-05T09:48:26.917983+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQSYSDK2XABNIACR","created_at":"2026-07-05T09:48:26.917983+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQSYSDK2","created_at":"2026-07-05T09:48:26.917983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27964","citing_title":"Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02828","citing_title":"NavCrafter: Exploring 3D Scenes from a Single Image","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6","json":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6.json","graph_json":"https://pith.science/api/pith-number/TQSYSDK2XABNIACRGG2KXN3CL6/graph.json","events_json":"https://pith.science/api/pith-number/TQSYSDK2XABNIACRGG2KXN3CL6/events.json","paper":"https://pith.science/paper/TQSYSDK2"},"agent_actions":{"view_html":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6","download_json":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6.json","view_paper":"https://pith.science/paper/TQSYSDK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09597&json=true","fetch_graph":"https://pith.science/api/pith-number/TQSYSDK2XABNIACRGG2KXN3CL6/graph.json","fetch_events":"https://pith.science/api/pith-number/TQSYSDK2XABNIACRGG2KXN3CL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6/action/storage_attestation","attest_author":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6/action/author_attestation","sign_citation":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6/action/citation_signature","submit_replication":"https://pith.science/pith/TQSYSDK2XABNIACRGG2KXN3CL6/action/replication_record"}},"created_at":"2026-07-05T09:48:26.917983+00:00","updated_at":"2026-07-05T09:48:26.917983+00:00"}