{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:775ZERCPCQ226BN7NXWG6AW6T7","short_pith_number":"pith:775ZERCP","schema_version":"1.0","canonical_sha256":"fffb92444f1435af05bf6dec6f02de9fe60d058177f4770dce3909eb1568f8d5","source":{"kind":"arxiv","id":"2607.27592","version":1},"attestation_state":"computed","paper":{"title":"MeshFM: 2D Features Are All You Need for 3D Shape Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Itai Lang, Jinfan Zhou, Rana Hanocka, Richard Liu","submitted_at":"2026-07-30T02:22:34Z","abstract_excerpt":"We present MeshFM, an efficient feedforward framework for extracting rich features from 3D inputs. Our method distills 2D features from visual foundation models into 3D. We train a feedforward network to directly predict 3D features without requiring optimization during inference. The approach utilizes a two-stage training strategy. First, we optimize a feature field in 3D using only 2D feature supervision. Second, we train a network to regress this feature field. The entire procedure requires no 3D annotation, instead relying on the powerful information in 2D foundation models. We demonstrate"},"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":"2607.27592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T02:22:34Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"b7dbfaa00af83e3f6e3691f24f721bc3423c4622208e525b714b8ab4d8c1686f","abstract_canon_sha256":"10e91893cb1a8e24626c623d91c08838a8b0a4ed01c6aefcc43781a56b7ee487"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fffb92444f1435af05bf6dec6f02de9fe60d058177f4770dce3909eb1568f8d5","last_reissued_at":"2026-07-31T01:26:52.188205Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:26:52.188205Z"},"graph_snapshot":{"paper":{"title":"MeshFM: 2D Features Are All You Need for 3D Shape Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Itai Lang, Jinfan Zhou, Rana Hanocka, Richard Liu","submitted_at":"2026-07-30T02:22:34Z","abstract_excerpt":"We present MeshFM, an efficient feedforward framework for extracting rich features from 3D inputs. Our method distills 2D features from visual foundation models into 3D. We train a feedforward network to directly predict 3D features without requiring optimization during inference. The approach utilizes a two-stage training strategy. First, we optimize a feature field in 3D using only 2D feature supervision. Second, we train a network to regress this feature field. The entire procedure requires no 3D annotation, instead relying on the powerful information in 2D foundation models. We demonstrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27592","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/2607.27592/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":"2607.27592","created_at":"2026-07-31T01:26:52.191220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27592v1","created_at":"2026-07-31T01:26:52.191220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27592","created_at":"2026-07-31T01:26:52.191220+00:00"},{"alias_kind":"pith_short_12","alias_value":"775ZERCPCQ22","created_at":"2026-07-31T01:26:52.191220+00:00"},{"alias_kind":"pith_short_16","alias_value":"775ZERCPCQ226BN7","created_at":"2026-07-31T01:26:52.191220+00:00"},{"alias_kind":"pith_short_8","alias_value":"775ZERCP","created_at":"2026-07-31T01:26:52.191220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7","json":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7.json","graph_json":"https://pith.science/api/pith-number/775ZERCPCQ226BN7NXWG6AW6T7/graph.json","events_json":"https://pith.science/api/pith-number/775ZERCPCQ226BN7NXWG6AW6T7/events.json","paper":"https://pith.science/paper/775ZERCP"},"agent_actions":{"view_html":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7","download_json":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7.json","view_paper":"https://pith.science/paper/775ZERCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27592&json=true","fetch_graph":"https://pith.science/api/pith-number/775ZERCPCQ226BN7NXWG6AW6T7/graph.json","fetch_events":"https://pith.science/api/pith-number/775ZERCPCQ226BN7NXWG6AW6T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7/action/storage_attestation","attest_author":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7/action/author_attestation","sign_citation":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7/action/citation_signature","submit_replication":"https://pith.science/pith/775ZERCPCQ226BN7NXWG6AW6T7/action/replication_record"}},"created_at":"2026-07-31T01:26:52.191220+00:00","updated_at":"2026-07-31T01:26:52.191220+00:00"}