{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JVU2TUEYVW52NRMBPLP2QHWAQB","short_pith_number":"pith:JVU2TUEY","schema_version":"1.0","canonical_sha256":"4d69a9d098adbba6c5817adfa81ec08053c7d0a6f297357bd3a87e0449a0b466","source":{"kind":"arxiv","id":"2404.16829","version":3},"attestation_state":"computed","paper":{"title":"Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Gordon Wetzstein, Jiaqi Wang, Tong Wu, Ye Fang, Zeyi Sun, Ziwei Liu","submitted_at":"2024-04-25T17:59:58Z","abstract_excerpt":"Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material libr"},"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":"2404.16829","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T17:59:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"de14e1b478328958b4af01b5d0eadda52a633ff18b713b98899ebb03b1d392fe","abstract_canon_sha256":"15467b8fea4cbb62d1a99dba3c812fff054971f438bd9653069d2c03713cf70c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:39.868359Z","signature_b64":"1drn/+v+ocPOavfSYAohWFO5uZyzk7uzNZ1ZvqdBVXn0c/K8rBryH/qPJ7QQvXu/R7BZEfGSXcwPSpK4wXxIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d69a9d098adbba6c5817adfa81ec08053c7d0a6f297357bd3a87e0449a0b466","last_reissued_at":"2026-07-05T08:22:39.867803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:39.867803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Gordon Wetzstein, Jiaqi Wang, Tong Wu, Ye Fang, Zeyi Sun, Ziwei Liu","submitted_at":"2024-04-25T17:59:58Z","abstract_excerpt":"Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material libr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16829","kind":"arxiv","version":3},"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/2404.16829/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":"2404.16829","created_at":"2026-07-05T08:22:39.867858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16829v3","created_at":"2026-07-05T08:22:39.867858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16829","created_at":"2026-07-05T08:22:39.867858+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVU2TUEYVW52","created_at":"2026-07-05T08:22:39.867858+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVU2TUEYVW52NRMB","created_at":"2026-07-05T08:22:39.867858+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVU2TUEY","created_at":"2026-07-05T08:22:39.867858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.22394","citing_title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16504","citing_title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06311","citing_title":"Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB","json":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB.json","graph_json":"https://pith.science/api/pith-number/JVU2TUEYVW52NRMBPLP2QHWAQB/graph.json","events_json":"https://pith.science/api/pith-number/JVU2TUEYVW52NRMBPLP2QHWAQB/events.json","paper":"https://pith.science/paper/JVU2TUEY"},"agent_actions":{"view_html":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB","download_json":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB.json","view_paper":"https://pith.science/paper/JVU2TUEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16829&json=true","fetch_graph":"https://pith.science/api/pith-number/JVU2TUEYVW52NRMBPLP2QHWAQB/graph.json","fetch_events":"https://pith.science/api/pith-number/JVU2TUEYVW52NRMBPLP2QHWAQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB/action/storage_attestation","attest_author":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB/action/author_attestation","sign_citation":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB/action/citation_signature","submit_replication":"https://pith.science/pith/JVU2TUEYVW52NRMBPLP2QHWAQB/action/replication_record"}},"created_at":"2026-07-05T08:22:39.867858+00:00","updated_at":"2026-07-05T08:22:39.867858+00:00"}