{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EBS4EPQABOMCDPGETHYZIMCSQ4","short_pith_number":"pith:EBS4EPQA","schema_version":"1.0","canonical_sha256":"2065c23e000b9821bcc499f1943052872b12b1073c7fc90bbf6f6ae3212de86e","source":{"kind":"arxiv","id":"2310.06773","version":1},"attestation_state":"computed","paper":{"title":"Uni3D: Exploring Unified 3D Representation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Jinsheng Wang, Junsheng Zhou, Tiejun Huang, Xinlong Wang, Yu-Shen Liu","submitted_at":"2023-10-10T16:49:21Z","abstract_excerpt":"Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language. However, scalable representation for 3D objects and scenes is relatively unexplored. In this work, we present Uni3D, a 3D foundation model to explore the unified 3D representation at scale. Uni3D uses a 2D initialized ViT end-to-end pretrained to align the 3D point cloud features with the image-text aligned features. Via the simple architecture and pretext task, Uni3D can leverage abundant 2D pretrained models as initialization and im"},"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":"2310.06773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T16:49:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"35f9c16b52875c80f19ccd82514045c8c65543f860021896d8f125096233ceeb","abstract_canon_sha256":"c5ccde7fbc84e2ce0e5d233a53a9ff47aaeea3d4adbf182d2b8b6ea5d8b83454"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:23.746169Z","signature_b64":"OnKxDFw3uNBTBaVPex3VXzVkOZMwhiU14yJJp7T0IfSyHD+UWSa2hfN2iIpT1IBDITZT2D+Wtg0gRhKqWcRkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2065c23e000b9821bcc499f1943052872b12b1073c7fc90bbf6f6ae3212de86e","last_reissued_at":"2026-07-05T06:59:23.745699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:23.745699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni3D: Exploring Unified 3D Representation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Jinsheng Wang, Junsheng Zhou, Tiejun Huang, Xinlong Wang, Yu-Shen Liu","submitted_at":"2023-10-10T16:49:21Z","abstract_excerpt":"Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language. However, scalable representation for 3D objects and scenes is relatively unexplored. In this work, we present Uni3D, a 3D foundation model to explore the unified 3D representation at scale. Uni3D uses a 2D initialized ViT end-to-end pretrained to align the 3D point cloud features with the image-text aligned features. Via the simple architecture and pretext task, Uni3D can leverage abundant 2D pretrained models as initialization and im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06773","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/2310.06773/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":"2310.06773","created_at":"2026-07-05T06:59:23.745758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06773v1","created_at":"2026-07-05T06:59:23.745758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06773","created_at":"2026-07-05T06:59:23.745758+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBS4EPQABOMC","created_at":"2026-07-05T06:59:23.745758+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBS4EPQABOMCDPGE","created_at":"2026-07-05T06:59:23.745758+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBS4EPQA","created_at":"2026-07-05T06:59:23.745758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06534","citing_title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25300","citing_title":"HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19828","citing_title":"3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07280","citing_title":"Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25300","citing_title":"HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26109","citing_title":"Helix4D: Complex 4D Mesh Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02060","citing_title":"CompassAD: Intent-Driven 3D Affordance Grounding in Functionally Competing Objects","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17620","citing_title":"SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18039","citing_title":"SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11232","citing_title":"DoReMi: Bridging 3D Domains via Topology-Aware Domain-Representation Mixture of Experts","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16567","citing_title":"POMA-3D: The Point Map Way to 3D Scene Understanding","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21331","citing_title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16504","citing_title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00937","citing_title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02546","citing_title":"RGB-Pointmap Pretraining for Unified 3D Scene Understanding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04050","citing_title":"TORA: Topological Representation Alignment for 3D Shape Assembly","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01365","citing_title":"VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00345","citing_title":"Pose-Aware Diffusion for 3D Generation","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16624","citing_title":"SAM 3D: 3Dfy Anything in Images","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15281","citing_title":"R3D: Revisiting 3D Policy Learning","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4","json":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4.json","graph_json":"https://pith.science/api/pith-number/EBS4EPQABOMCDPGETHYZIMCSQ4/graph.json","events_json":"https://pith.science/api/pith-number/EBS4EPQABOMCDPGETHYZIMCSQ4/events.json","paper":"https://pith.science/paper/EBS4EPQA"},"agent_actions":{"view_html":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4","download_json":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4.json","view_paper":"https://pith.science/paper/EBS4EPQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06773&json=true","fetch_graph":"https://pith.science/api/pith-number/EBS4EPQABOMCDPGETHYZIMCSQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/EBS4EPQABOMCDPGETHYZIMCSQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4/action/storage_attestation","attest_author":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4/action/author_attestation","sign_citation":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4/action/citation_signature","submit_replication":"https://pith.science/pith/EBS4EPQABOMCDPGETHYZIMCSQ4/action/replication_record"}},"created_at":"2026-07-05T06:59:23.745758+00:00","updated_at":"2026-07-05T06:59:23.745758+00:00"}