{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q5FKK7DKSFFSVRNXZINE2UQHQ2","short_pith_number":"pith:Q5FKK7DK","schema_version":"1.0","canonical_sha256":"874aa57c6a914b2ac5b7ca1a4d520786a72b9685361723b5e39fa928bd9a7726","source":{"kind":"arxiv","id":"2403.08902","version":1},"attestation_state":"computed","paper":{"title":"Envision3D: One Image to 3D with Anchor Views Interpolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francis E.H. Tay, Junwu Zhang, Li Yuan, Tanghui Jia, Xing Zhou, Xinhua Cheng, Yatian Pang, Yujun Shi, Zhenyu Tang","submitted_at":"2024-03-13T18:46:33Z","abstract_excerpt":"We present Envision3D, a novel method for efficiently generating high-quality 3D content from a single image. Recent methods that extract 3D content from multi-view images generated by diffusion models show great potential. However, it is still challenging for diffusion models to generate dense multi-view consistent images, which is crucial for the quality of 3D content extraction. To address this issue, we propose a novel cascade diffusion framework, which decomposes the challenging dense views generation task into two tractable stages, namely anchor views generation and anchor views interpol"},"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":"2403.08902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T18:46:33Z","cross_cats_sorted":[],"title_canon_sha256":"ea612ff66257f01be5293a7e5e0bdc68fb2e1cee004aecde83912b5b3c73e079","abstract_canon_sha256":"ec95b6221975ab9c69bd5e2dfcc6920ea1cc3c1a0ed9879d46dda0f469c23539"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:48.903121Z","signature_b64":"5FIZtgSX5IY0tSCyoktnsDdHkEalvXuF0jujpD9AYNbJRjf6bAsB064yA/LIst9X9HLqJCLto5dUmLD6Xr/mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874aa57c6a914b2ac5b7ca1a4d520786a72b9685361723b5e39fa928bd9a7726","last_reissued_at":"2026-07-05T07:55:48.902645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:48.902645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Envision3D: One Image to 3D with Anchor Views Interpolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francis E.H. Tay, Junwu Zhang, Li Yuan, Tanghui Jia, Xing Zhou, Xinhua Cheng, Yatian Pang, Yujun Shi, Zhenyu Tang","submitted_at":"2024-03-13T18:46:33Z","abstract_excerpt":"We present Envision3D, a novel method for efficiently generating high-quality 3D content from a single image. Recent methods that extract 3D content from multi-view images generated by diffusion models show great potential. However, it is still challenging for diffusion models to generate dense multi-view consistent images, which is crucial for the quality of 3D content extraction. To address this issue, we propose a novel cascade diffusion framework, which decomposes the challenging dense views generation task into two tractable stages, namely anchor views generation and anchor views interpol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08902","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/2403.08902/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":"2403.08902","created_at":"2026-07-05T07:55:48.902703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08902v1","created_at":"2026-07-05T07:55:48.902703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08902","created_at":"2026-07-05T07:55:48.902703+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5FKK7DKSFFS","created_at":"2026-07-05T07:55:48.902703+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5FKK7DKSFFSVRNX","created_at":"2026-07-05T07:55:48.902703+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5FKK7DK","created_at":"2026-07-05T07:55:48.902703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07700","citing_title":"Make Your MoVe: Make Your 3D Contents by Adapting Multi-View Diffusion Models to External Editing","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2","json":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2.json","graph_json":"https://pith.science/api/pith-number/Q5FKK7DKSFFSVRNXZINE2UQHQ2/graph.json","events_json":"https://pith.science/api/pith-number/Q5FKK7DKSFFSVRNXZINE2UQHQ2/events.json","paper":"https://pith.science/paper/Q5FKK7DK"},"agent_actions":{"view_html":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2","download_json":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2.json","view_paper":"https://pith.science/paper/Q5FKK7DK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08902&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5FKK7DKSFFSVRNXZINE2UQHQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5FKK7DKSFFSVRNXZINE2UQHQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2/action/storage_attestation","attest_author":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2/action/author_attestation","sign_citation":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2/action/citation_signature","submit_replication":"https://pith.science/pith/Q5FKK7DKSFFSVRNXZINE2UQHQ2/action/replication_record"}},"created_at":"2026-07-05T07:55:48.902703+00:00","updated_at":"2026-07-05T07:55:48.902703+00:00"}