{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XKRS3Z7RTYURWBSU2RVUVCP6M3","short_pith_number":"pith:XKRS3Z7R","schema_version":"1.0","canonical_sha256":"baa32de7f19e291b0654d46b4a89fe66c20c42a0c169250e495b222a7550c65b","source":{"kind":"arxiv","id":"2310.15110","version":1},"attestation_state":"computed","paper":{"title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Targeted conditioning on Stable Diffusion lets a model turn one image into geometrically consistent multi-view outputs.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chong Zeng, Hansheng Chen, Hao Su, Linghao Chen, Minghua Liu, Ruoxi Shi, Xinyue Wei, Zhuoyang Zhang","submitted_at":"2023-10-23T17:18:59Z","abstract_excerpt":"We report Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view. To take full advantage of pretrained 2D generative priors, we develop various conditioning and training schemes to minimize the effort of finetuning from off-the-shelf image diffusion models such as Stable Diffusion. Zero123++ excels in producing high-quality, consistent multi-view images from a single image, overcoming common issues like texture degradation and geometric misalignment. Furthermore, we showcase the feasibility of training a ControlNet on Zero123++ f"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2310.15110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:18:59Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"28fe4b7db9f6d08983e633f2a43bf8e9673fdc0b955f677d84d6eda1f4a58e54","abstract_canon_sha256":"279ce4061af587502604cef8527fe134497e45b0f384e3acc22d69167d69254d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.429912Z","signature_b64":"ugntKL0KqA6rBxccQfq+SEE+/weLyG4fJ6DHri82F24HMiroFYkP6/qs2htqVtVc8wxOjL2EWvhXQx9iocdPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baa32de7f19e291b0654d46b4a89fe66c20c42a0c169250e495b222a7550c65b","last_reissued_at":"2026-05-17T23:38:46.429454Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.429454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Targeted conditioning on Stable Diffusion lets a model turn one image into geometrically consistent multi-view outputs.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chong Zeng, Hansheng Chen, Hao Su, Linghao Chen, Minghua Liu, Ruoxi Shi, Xinyue Wei, Zhuoyang Zhang","submitted_at":"2023-10-23T17:18:59Z","abstract_excerpt":"We report Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view. To take full advantage of pretrained 2D generative priors, we develop various conditioning and training schemes to minimize the effort of finetuning from off-the-shelf image diffusion models such as Stable Diffusion. Zero123++ excels in producing high-quality, consistent multi-view images from a single image, overcoming common issues like texture degradation and geometric misalignment. Furthermore, we showcase the feasibility of training a ControlNet on Zero123++ f"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Zero123++ excels in producing high-quality, consistent multi-view images from a single image, overcoming common issues like texture degradation and geometric misalignment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed conditioning and training schemes applied to off-the-shelf Stable Diffusion will reliably produce 3D geometric and texture consistency without new failure modes not captured in the reported examples.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Zero123++ produces high-quality 3D-consistent multi-view images from a single input by fine-tuning Stable Diffusion with targeted conditioning and training methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Targeted conditioning on Stable Diffusion lets a model turn one image into geometrically consistent multi-view outputs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"27309c20f661e36843a3a6d0bd4f0488b55ad7edcb966c6323c76780c4d6b861"},"source":{"id":"2310.15110","kind":"arxiv","version":1},"verdict":{"id":"6ccedf79-be9d-4db0-a380-f29a2dd2850f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T22:02:36.780458Z","strongest_claim":"Zero123++ excels in producing high-quality, consistent multi-view images from a single image, overcoming common issues like texture degradation and geometric misalignment.","one_line_summary":"Zero123++ produces high-quality 3D-consistent multi-view images from a single input by fine-tuning Stable Diffusion with targeted conditioning and training methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed conditioning and training schemes applied to off-the-shelf Stable Diffusion will reliably produce 3D geometric and texture consistency without new failure modes not captured in the reported examples.","pith_extraction_headline":"Targeted conditioning on Stable Diffusion lets a model turn one image into geometrically consistent multi-view outputs."},"references":{"count":26,"sample":[{"doi":"","year":2015,"title":"ShapeNet: An Information-Rich 3D Model Repository","work_id":"b2ac5b60-daa9-435b-9369-12271e126edd","ref_index":1,"cited_arxiv_id":"1512.03012","is_internal_anchor":true},{"doi":"","year":2023,"title":"On the importance of noise scheduling for diffusion models","work_id":"1783cbc7-505c-4ebc-82f3-86877ef131b3","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Objaverse-XL: A Universe of 10M+ 3D Objects","work_id":"1c5475ad-d1ec-4de1-8670-b8cd5a4c85d3","ref_index":3,"cited_arxiv_id":"2307.05663","is_internal_anchor":true},{"doi":"","year":2023,"title":"Objaverse: A universe of annotated 3d objects","work_id":"d953dbea-284d-4b7a-a33b-2454de5cc2e6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Efficient diffu- sion training via min-snr weighting strategy","work_id":"f908ce8d-6164-45c4-afa4-11df4ae81e42","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":26,"snapshot_sha256":"e3d112cbf41fd9359e870781ecffd0218dafb2e0d8a945725ff827a0bbf9648e","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fdadcfd782e68c99c15a1ec9bee7e9910e1b542ce7634f07aaa399adaa604555"},"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":"2310.15110","created_at":"2026-05-17T23:38:46.429529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15110v1","created_at":"2026-05-17T23:38:46.429529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15110","created_at":"2026-05-17T23:38:46.429529+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKRS3Z7RTYUR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKRS3Z7RTYURWBSU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKRS3Z7R","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2501.03717","citing_title":"Materialist: Physically Based Editing Using Single-Image Inverse Rendering","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16766","citing_title":"SVG360: Editable Multiview Vector Graphics from a Single SVG","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20733","citing_title":"Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16355","citing_title":"Generative 3D Gaussians with Learned Density Control","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19865","citing_title":"Landscape-Awareness for Geometric View Diffusion Model","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2505.22394","citing_title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04236","citing_title":"Scaling Sequence-to-Sequence Generative Neural Rendering","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15442","citing_title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2506.16504","citing_title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13852","citing_title":"Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2404.07191","citing_title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2405.05941","citing_title":"Evaluating Real-World Robot Manipulation Policies in Simulation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12399","citing_title":"GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27422","citing_title":"Sparse-View 3D Gaussian Splatting in the Wild","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3","json":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3.json","graph_json":"https://pith.science/api/pith-number/XKRS3Z7RTYURWBSU2RVUVCP6M3/graph.json","events_json":"https://pith.science/api/pith-number/XKRS3Z7RTYURWBSU2RVUVCP6M3/events.json","paper":"https://pith.science/paper/XKRS3Z7R"},"agent_actions":{"view_html":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3","download_json":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3.json","view_paper":"https://pith.science/paper/XKRS3Z7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15110&json=true","fetch_graph":"https://pith.science/api/pith-number/XKRS3Z7RTYURWBSU2RVUVCP6M3/graph.json","fetch_events":"https://pith.science/api/pith-number/XKRS3Z7RTYURWBSU2RVUVCP6M3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3/action/storage_attestation","attest_author":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3/action/author_attestation","sign_citation":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3/action/citation_signature","submit_replication":"https://pith.science/pith/XKRS3Z7RTYURWBSU2RVUVCP6M3/action/replication_record"}},"created_at":"2026-05-17T23:38:46.429529+00:00","updated_at":"2026-05-17T23:38:46.429529+00:00"}