{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R6S4ZXQUVJ7YWTX5FG5S4OB26I","short_pith_number":"pith:R6S4ZXQU","schema_version":"1.0","canonical_sha256":"8fa5ccde14aa7f8b4efd29bb2e383af21aecb385d3fa605410252b4804943be0","source":{"kind":"arxiv","id":"2404.16538","version":3},"attestation_state":"computed","paper":{"title":"OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Ye Mao","submitted_at":"2024-04-25T11:53:36Z","abstract_excerpt":"Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D point cloud with image-text information have shown superior 3D zero-shot performance. However, CAD-rendered images for this alignment often lack realism and texture variation, compromising alignment robustness. Moreover, the volume discrepancy between 3D and 2D pretraining datasets highlights the need for effective strategies to transfer the representational abilities of VLMs to 3D learning. In this paper, we present OpenDlign, a novel open-world 3D model using depth-aligned images generated fr"},"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":"2404.16538","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T11:53:36Z","cross_cats_sorted":[],"title_canon_sha256":"381fdedf99de9a5a042f2fa7ccd077f0736aec6eb664f6d3f53b3941d2933ad6","abstract_canon_sha256":"ef2dd50cc54623e32a030ba61310eff7122040fd9df71a7cfef2a75bd333406d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:02.038798Z","signature_b64":"lk9pj0OWMqnTQickpNE9uYGOd5YCKa00jV09PsiHdEATtM9loI8aUr7o2phpVjNctBa9t07+cyyqWpj99an5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa5ccde14aa7f8b4efd29bb2e383af21aecb385d3fa605410252b4804943be0","last_reissued_at":"2026-07-05T09:13:02.038254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:02.038254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Ye Mao","submitted_at":"2024-04-25T11:53:36Z","abstract_excerpt":"Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D point cloud with image-text information have shown superior 3D zero-shot performance. However, CAD-rendered images for this alignment often lack realism and texture variation, compromising alignment robustness. Moreover, the volume discrepancy between 3D and 2D pretraining datasets highlights the need for effective strategies to transfer the representational abilities of VLMs to 3D learning. In this paper, we present OpenDlign, a novel open-world 3D model using depth-aligned images generated fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16538","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/2404.16538/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":"2404.16538","created_at":"2026-07-05T09:13:02.038307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16538v3","created_at":"2026-07-05T09:13:02.038307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16538","created_at":"2026-07-05T09:13:02.038307+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6S4ZXQUVJ7Y","created_at":"2026-07-05T09:13:02.038307+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6S4ZXQUVJ7YWTX5","created_at":"2026-07-05T09:13:02.038307+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6S4ZXQU","created_at":"2026-07-05T09:13:02.038307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00954","citing_title":"Hypo3D: Exploring Hypothetical Reasoning in 3D","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I","json":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I.json","graph_json":"https://pith.science/api/pith-number/R6S4ZXQUVJ7YWTX5FG5S4OB26I/graph.json","events_json":"https://pith.science/api/pith-number/R6S4ZXQUVJ7YWTX5FG5S4OB26I/events.json","paper":"https://pith.science/paper/R6S4ZXQU"},"agent_actions":{"view_html":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I","download_json":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I.json","view_paper":"https://pith.science/paper/R6S4ZXQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16538&json=true","fetch_graph":"https://pith.science/api/pith-number/R6S4ZXQUVJ7YWTX5FG5S4OB26I/graph.json","fetch_events":"https://pith.science/api/pith-number/R6S4ZXQUVJ7YWTX5FG5S4OB26I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I/action/storage_attestation","attest_author":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I/action/author_attestation","sign_citation":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I/action/citation_signature","submit_replication":"https://pith.science/pith/R6S4ZXQUVJ7YWTX5FG5S4OB26I/action/replication_record"}},"created_at":"2026-07-05T09:13:02.038307+00:00","updated_at":"2026-07-05T09:13:02.038307+00:00"}