{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CXOLJ4KYBWMBHVSGFWG5PWFKJW","short_pith_number":"pith:CXOLJ4KY","schema_version":"1.0","canonical_sha256":"15dcb4f1580d9813d6462d8dd7d8aa4db13f859abbcb0d777852d4feef02c0a6","source":{"kind":"arxiv","id":"2504.17670","version":2},"attestation_state":"computed","paper":{"title":"DiMeR: Disentangled Mesh Reconstruction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiantao Lin, Kanghao Chen, Lutao Jiang, Wenhang Ge, Xin Yang, Xu Zheng, Yifan Jiang, Yinchuan Li, Yingcong Chen, Yuanhuiyi Lyu","submitted_at":"2025-04-24T15:39:20Z","abstract_excerpt":"We propose DiMeR, a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction. Existing methods confront two persistent obstacles: (i) textures can conceal geometric errors, i.e., visually plausible images can be rendered even with wrong geometry, producing multiple ambiguous optimization objectives in geometry-texture mixed solution space for similar objects; and (ii) prevailing mesh extraction methods are redundant, unstable, and lack 3D supervision. To solve these challenges, we rethink the inductive bias for mesh reconstruction. First, w"},"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":"2504.17670","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T15:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"8b8761802355e6cadfe4c2144510da8b486a8348049cd9390a760d4e2bde872e","abstract_canon_sha256":"74c570750a2cfa09b9a26d4cdf7b157b39b375bdb5c34a400e774f97c1f27b34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:11.948691Z","signature_b64":"WORer8j4M/gmQJTBxyq7f+tB/uZ0yA/USBpZ1XTSGe2e6VCdf2vKCqoJuNDneXaySRPoAKaB8WMMb5gzjYaKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15dcb4f1580d9813d6462d8dd7d8aa4db13f859abbcb0d777852d4feef02c0a6","last_reissued_at":"2026-07-05T11:09:11.948196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:11.948196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiMeR: Disentangled Mesh Reconstruction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiantao Lin, Kanghao Chen, Lutao Jiang, Wenhang Ge, Xin Yang, Xu Zheng, Yifan Jiang, Yinchuan Li, Yingcong Chen, Yuanhuiyi Lyu","submitted_at":"2025-04-24T15:39:20Z","abstract_excerpt":"We propose DiMeR, a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction. Existing methods confront two persistent obstacles: (i) textures can conceal geometric errors, i.e., visually plausible images can be rendered even with wrong geometry, producing multiple ambiguous optimization objectives in geometry-texture mixed solution space for similar objects; and (ii) prevailing mesh extraction methods are redundant, unstable, and lack 3D supervision. To solve these challenges, we rethink the inductive bias for mesh reconstruction. First, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17670","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/2504.17670/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":"2504.17670","created_at":"2026-07-05T11:09:11.948253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17670v2","created_at":"2026-07-05T11:09:11.948253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17670","created_at":"2026-07-05T11:09:11.948253+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXOLJ4KYBWMB","created_at":"2026-07-05T11:09:11.948253+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXOLJ4KYBWMBHVSG","created_at":"2026-07-05T11:09:11.948253+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXOLJ4KY","created_at":"2026-07-05T11:09:11.948253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.01030","citing_title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW","json":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW.json","graph_json":"https://pith.science/api/pith-number/CXOLJ4KYBWMBHVSGFWG5PWFKJW/graph.json","events_json":"https://pith.science/api/pith-number/CXOLJ4KYBWMBHVSGFWG5PWFKJW/events.json","paper":"https://pith.science/paper/CXOLJ4KY"},"agent_actions":{"view_html":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW","download_json":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW.json","view_paper":"https://pith.science/paper/CXOLJ4KY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17670&json=true","fetch_graph":"https://pith.science/api/pith-number/CXOLJ4KYBWMBHVSGFWG5PWFKJW/graph.json","fetch_events":"https://pith.science/api/pith-number/CXOLJ4KYBWMBHVSGFWG5PWFKJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW/action/storage_attestation","attest_author":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW/action/author_attestation","sign_citation":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW/action/citation_signature","submit_replication":"https://pith.science/pith/CXOLJ4KYBWMBHVSGFWG5PWFKJW/action/replication_record"}},"created_at":"2026-07-05T11:09:11.948253+00:00","updated_at":"2026-07-05T11:09:11.948253+00:00"}