{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4MSJCO2VUO6Y6KKRVC2OD7APRC","short_pith_number":"pith:4MSJCO2V","schema_version":"1.0","canonical_sha256":"e324913b55a3bd8f2951a8b4e1fc0f88ba5647c1b1c884b13410466a67727b6a","source":{"kind":"arxiv","id":"2306.17843","version":2},"attestation_state":"computed","paper":{"title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah Hamdi, Aliaksandr Siarohin, Bernard Ghanem, Bing Li, Guocheng Qian, Hsin-Ying Lee, Ivan Skorokhodov, Jian Ren, Jinjie Mai, Peter Wonka, Sergey Tulyakov","submitted_at":"2023-06-30T17:59:08Z","abstract_excerpt":"We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter "},"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":"2306.17843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-30T17:59:08Z","cross_cats_sorted":[],"title_canon_sha256":"568aa0e09fd12c411dcea8f57cdbc1c338f3dbff65d0a49e8866283d8981cea6","abstract_canon_sha256":"745a127ac78e839e71097d47f4db544db3cfcfc4691e987dd0729581578b5be1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:46.777788Z","signature_b64":"N0Qv6OmLa73diQKyCPTinnOJfYtAs0Xwy/UqjKrkTorkBmSSsIwAY2M1Na2gA13LBejWPsI1P6oC25SKU1d3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e324913b55a3bd8f2951a8b4e1fc0f88ba5647c1b1c884b13410466a67727b6a","last_reissued_at":"2026-07-05T06:33:46.777290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:46.777290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdullah Hamdi, Aliaksandr Siarohin, Bernard Ghanem, Bing Li, Guocheng Qian, Hsin-Ying Lee, Ivan Skorokhodov, Jian Ren, Jinjie Mai, Peter Wonka, Sergey Tulyakov","submitted_at":"2023-06-30T17:59:08Z","abstract_excerpt":"We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17843","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/2306.17843/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":"2306.17843","created_at":"2026-07-05T06:33:46.777385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17843v2","created_at":"2026-07-05T06:33:46.777385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17843","created_at":"2026-07-05T06:33:46.777385+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MSJCO2VUO6Y","created_at":"2026-07-05T06:33:46.777385+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MSJCO2VUO6Y6KKR","created_at":"2026-07-05T06:33:46.777385+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MSJCO2V","created_at":"2026-07-05T06:33:46.777385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06565","citing_title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21596","citing_title":"$\\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08440","citing_title":"GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":248,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16764","citing_title":"BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2405.10314","citing_title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16653","citing_title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04400","citing_title":"LRM: Large Reconstruction Model for Single Image to 3D","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07191","citing_title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09231","citing_title":"Hitem3D 2.0: Multi-View Guided Native 3D Texture Generation","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC","json":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC.json","graph_json":"https://pith.science/api/pith-number/4MSJCO2VUO6Y6KKRVC2OD7APRC/graph.json","events_json":"https://pith.science/api/pith-number/4MSJCO2VUO6Y6KKRVC2OD7APRC/events.json","paper":"https://pith.science/paper/4MSJCO2V"},"agent_actions":{"view_html":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC","download_json":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC.json","view_paper":"https://pith.science/paper/4MSJCO2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17843&json=true","fetch_graph":"https://pith.science/api/pith-number/4MSJCO2VUO6Y6KKRVC2OD7APRC/graph.json","fetch_events":"https://pith.science/api/pith-number/4MSJCO2VUO6Y6KKRVC2OD7APRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC/action/storage_attestation","attest_author":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC/action/author_attestation","sign_citation":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC/action/citation_signature","submit_replication":"https://pith.science/pith/4MSJCO2VUO6Y6KKRVC2OD7APRC/action/replication_record"}},"created_at":"2026-07-05T06:33:46.777385+00:00","updated_at":"2026-07-05T06:33:46.777385+00:00"}