{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HTD5ISB6DEMSMQV3WFKW5QS4QR","short_pith_number":"pith:HTD5ISB6","schema_version":"1.0","canonical_sha256":"3cc7d4483e19192642bbb1556ec25c8456724657785f710521ccf86453236e07","source":{"kind":"arxiv","id":"2312.04424","version":2},"attestation_state":"computed","paper":{"title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Hongkai Xiong, Jiemin Fang, Lingxi Xie, Qi Tian, Taoran Yi, Wenrui Dai, Xiaopeng Zhang, Xinggang Wang, Yabo Chen, Yuyang Huang","submitted_at":"2023-12-07T16:49:09Z","abstract_excerpt":"Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a single-view source image and the camera pose as condition information. However, due to the high sparsity of the single input image, Zero-1-to-3 tends to produce geometry and appearance inconsistency across views, especially for complex objects. To tackle this issue, we propose to supply more condition information for the generation model but in a self-prompt way. "},"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":"2312.04424","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T16:49:09Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"015a223fefa18dfa07321e4b3590fa798835b77ee2d75cd74bffe6c2e34e4a00","abstract_canon_sha256":"fd67081410bc9db8617823bf644eea3d053e13b8869e9d328f1205a83321f38f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:18.752497Z","signature_b64":"HsT+q1uq3m3qQUBfQiLqQ5JhESGS0/C4h06VEs+f7NL0GV4+taSKPHiiaMvA0m/XRpVWoXDrH6b/cm3Lbz2jDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cc7d4483e19192642bbb1556ec25c8456724657785f710521ccf86453236e07","last_reissued_at":"2026-07-05T08:53:18.751885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:18.751885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Hongkai Xiong, Jiemin Fang, Lingxi Xie, Qi Tian, Taoran Yi, Wenrui Dai, Xiaopeng Zhang, Xinggang Wang, Yabo Chen, Yuyang Huang","submitted_at":"2023-12-07T16:49:09Z","abstract_excerpt":"Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a single-view source image and the camera pose as condition information. However, due to the high sparsity of the single input image, Zero-1-to-3 tends to produce geometry and appearance inconsistency across views, especially for complex objects. To tackle this issue, we propose to supply more condition information for the generation model but in a self-prompt way. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04424","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/2312.04424/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":"2312.04424","created_at":"2026-07-05T08:53:18.751955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04424v2","created_at":"2026-07-05T08:53:18.751955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04424","created_at":"2026-07-05T08:53:18.751955+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTD5ISB6DEMS","created_at":"2026-07-05T08:53:18.751955+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTD5ISB6DEMSMQV3","created_at":"2026-07-05T08:53:18.751955+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTD5ISB6","created_at":"2026-07-05T08:53:18.751955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR","json":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR.json","graph_json":"https://pith.science/api/pith-number/HTD5ISB6DEMSMQV3WFKW5QS4QR/graph.json","events_json":"https://pith.science/api/pith-number/HTD5ISB6DEMSMQV3WFKW5QS4QR/events.json","paper":"https://pith.science/paper/HTD5ISB6"},"agent_actions":{"view_html":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR","download_json":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR.json","view_paper":"https://pith.science/paper/HTD5ISB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04424&json=true","fetch_graph":"https://pith.science/api/pith-number/HTD5ISB6DEMSMQV3WFKW5QS4QR/graph.json","fetch_events":"https://pith.science/api/pith-number/HTD5ISB6DEMSMQV3WFKW5QS4QR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR/action/storage_attestation","attest_author":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR/action/author_attestation","sign_citation":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR/action/citation_signature","submit_replication":"https://pith.science/pith/HTD5ISB6DEMSMQV3WFKW5QS4QR/action/replication_record"}},"created_at":"2026-07-05T08:53:18.751955+00:00","updated_at":"2026-07-05T08:53:18.751955+00:00"}