{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2BUKEFPLMXRZUZKY7MJXPMA2JG","short_pith_number":"pith:2BUKEFPL","schema_version":"1.0","canonical_sha256":"d068a215eb65e39a6558fb1377b01a4990deb672db1d540d2653785e927d55b7","source":{"kind":"arxiv","id":"2407.14979","version":4},"attestation_state":"computed","paper":{"title":"RGB2Point: 3D Point Cloud Generation from Single RGB Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bedrich Benes, Jae Joong Lee","submitted_at":"2024-07-20T21:06:33Z","abstract_excerpt":"We introduce RGB2Point, an unposed single-view RGB image to a 3D point cloud generation based on Transformer. RGB2Point takes an input image of an object and generates a dense 3D point cloud. Contrary to prior works based on CNN layers and diffusion denoising approaches, we use pre-trained Transformer layers that are fast and generate high-quality point clouds with consistent quality over available categories. Our generated point clouds demonstrate high quality on a real-world dataset, as evidenced by improved Chamfer distance (51.15%) and Earth Mover's distance (45.96%) metrics compared to th"},"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":"2407.14979","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-20T21:06:33Z","cross_cats_sorted":[],"title_canon_sha256":"8ac47d3c3ba52aaacc32f10b47bfbd7729c38dbc26754ee8fdc55e44096bcf46","abstract_canon_sha256":"1e9be58236375a4137c3dec111f44bc2ea4bed80311375ee382a83ee5003f8ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:35.251668Z","signature_b64":"4tFT9qQtcWEWFBhcRh1PTbBqCMXT2odGxAUjwcEgjSaVO5QtkVGdtA/kWfA0Lk2NsLp8hYjiO8qltF5ZqUMHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d068a215eb65e39a6558fb1377b01a4990deb672db1d540d2653785e927d55b7","last_reissued_at":"2026-07-05T09:44:35.251136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:35.251136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RGB2Point: 3D Point Cloud Generation from Single RGB Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bedrich Benes, Jae Joong Lee","submitted_at":"2024-07-20T21:06:33Z","abstract_excerpt":"We introduce RGB2Point, an unposed single-view RGB image to a 3D point cloud generation based on Transformer. RGB2Point takes an input image of an object and generates a dense 3D point cloud. Contrary to prior works based on CNN layers and diffusion denoising approaches, we use pre-trained Transformer layers that are fast and generate high-quality point clouds with consistent quality over available categories. Our generated point clouds demonstrate high quality on a real-world dataset, as evidenced by improved Chamfer distance (51.15%) and Earth Mover's distance (45.96%) metrics compared to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14979","kind":"arxiv","version":4},"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/2407.14979/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":"2407.14979","created_at":"2026-07-05T09:44:35.251192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14979v4","created_at":"2026-07-05T09:44:35.251192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14979","created_at":"2026-07-05T09:44:35.251192+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BUKEFPLMXRZ","created_at":"2026-07-05T09:44:35.251192+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BUKEFPLMXRZUZKY","created_at":"2026-07-05T09:44:35.251192+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BUKEFPL","created_at":"2026-07-05T09:44:35.251192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07575","citing_title":"Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG","json":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG.json","graph_json":"https://pith.science/api/pith-number/2BUKEFPLMXRZUZKY7MJXPMA2JG/graph.json","events_json":"https://pith.science/api/pith-number/2BUKEFPLMXRZUZKY7MJXPMA2JG/events.json","paper":"https://pith.science/paper/2BUKEFPL"},"agent_actions":{"view_html":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG","download_json":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG.json","view_paper":"https://pith.science/paper/2BUKEFPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14979&json=true","fetch_graph":"https://pith.science/api/pith-number/2BUKEFPLMXRZUZKY7MJXPMA2JG/graph.json","fetch_events":"https://pith.science/api/pith-number/2BUKEFPLMXRZUZKY7MJXPMA2JG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG/action/storage_attestation","attest_author":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG/action/author_attestation","sign_citation":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG/action/citation_signature","submit_replication":"https://pith.science/pith/2BUKEFPLMXRZUZKY7MJXPMA2JG/action/replication_record"}},"created_at":"2026-07-05T09:44:35.251192+00:00","updated_at":"2026-07-05T09:44:35.251192+00:00"}