{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JAJZHMQKVWLFAQJPYQ26MOKRPS","short_pith_number":"pith:JAJZHMQK","schema_version":"1.0","canonical_sha256":"481393b20aad9650412fc435e639517c9948695242111ef51aa1f3e3fcccbaac","source":{"kind":"arxiv","id":"2408.10198","version":1},"attestation_state":"computed","paper":{"title":"MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chong Zeng, Hao Su, Hongzhi Wu, Isabella Liu, Linghao Chen, Mengqi Zhang, Minghua Liu, Ruoxi Shi, Xiaoshuai Zhang, Xinyue Wei, Zhaoning Wang","submitted_at":"2024-08-19T17:55:17Z","abstract_excerpt":"Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. I"},"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":"2408.10198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T17:55:17Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"c1836e892f0dc4717ecc3a9af3043de9f81dd6f5334b650b9693f6bca447ee0f","abstract_canon_sha256":"cb8496eb07ca7ee46c88c8df7bf9d60a79057e683898c2a0d534ec89cea65d22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:53.050229Z","signature_b64":"JkrX65QZzLo0x5n2FMhrrztKzsfdVOgwVmRZSWYRdPcPvq3DG4LdwEXZkG93ewdf7Fu//uPd6HJ/55jPT2mJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"481393b20aad9650412fc435e639517c9948695242111ef51aa1f3e3fcccbaac","last_reissued_at":"2026-07-05T08:56:53.049785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:53.049785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chong Zeng, Hao Su, Hongzhi Wu, Isabella Liu, Linghao Chen, Mengqi Zhang, Minghua Liu, Ruoxi Shi, Xiaoshuai Zhang, Xinyue Wei, Zhaoning Wang","submitted_at":"2024-08-19T17:55:17Z","abstract_excerpt":"Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In this work, we introduce MeshFormer, a sparse-view reconstruction model that explicitly leverages 3D native structure, input guidance, and training supervision. Specifically, instead of using a triplane representation, we store features in 3D sparse voxels and combine transformers with 3D convolutions to leverage an explicit 3D structure and projective bias. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10198","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/2408.10198/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":"2408.10198","created_at":"2026-07-05T08:56:53.049842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10198v1","created_at":"2026-07-05T08:56:53.049842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10198","created_at":"2026-07-05T08:56:53.049842+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAJZHMQKVWLF","created_at":"2026-07-05T08:56:53.049842+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAJZHMQKVWLFAQJP","created_at":"2026-07-05T08:56:53.049842+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAJZHMQK","created_at":"2026-07-05T08:56:53.049842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS","json":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS.json","graph_json":"https://pith.science/api/pith-number/JAJZHMQKVWLFAQJPYQ26MOKRPS/graph.json","events_json":"https://pith.science/api/pith-number/JAJZHMQKVWLFAQJPYQ26MOKRPS/events.json","paper":"https://pith.science/paper/JAJZHMQK"},"agent_actions":{"view_html":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS","download_json":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS.json","view_paper":"https://pith.science/paper/JAJZHMQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10198&json=true","fetch_graph":"https://pith.science/api/pith-number/JAJZHMQKVWLFAQJPYQ26MOKRPS/graph.json","fetch_events":"https://pith.science/api/pith-number/JAJZHMQKVWLFAQJPYQ26MOKRPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS/action/storage_attestation","attest_author":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS/action/author_attestation","sign_citation":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS/action/citation_signature","submit_replication":"https://pith.science/pith/JAJZHMQKVWLFAQJPYQ26MOKRPS/action/replication_record"}},"created_at":"2026-07-05T08:56:53.049842+00:00","updated_at":"2026-07-05T08:56:53.049842+00:00"}