{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TAJPPPQG2V2KZBCDOPK3DLAEEF","short_pith_number":"pith:TAJPPPQG","schema_version":"1.0","canonical_sha256":"9812f7be06d574ac844373d5b1ac042151e7d2f4344bddf371eba5c2751f49ff","source":{"kind":"arxiv","id":"2403.02151","version":1},"attestation_state":"computed","paper":{"title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TripoSR produces a 3D mesh from one photo in under half a second by refining the LRM transformer design.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Letts, Christian Laforte, David Pankratz, Ding Liang, Dmitry Tochilkin, Varun Jampani, Yangguang Li, Yan-Pei Cao, Zexiang Liu, Zixuan Huang","submitted_at":"2024-03-04T16:00:56Z","abstract_excerpt":"This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0.5 seconds. Building upon the LRM network architecture, TripoSR integrates substantial improvements in data processing, model design, and training techniques. Evaluations on public datasets show that TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives. Released under the MIT license, TripoSR is intended to empower researchers, developers, a"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.02151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T16:00:56Z","cross_cats_sorted":[],"title_canon_sha256":"ff1307898b180369139ca90be26449a5e56e4499cef9c5fd27bfca8cb8bbed7f","abstract_canon_sha256":"4abd47535d04c2de8375e128ccda5195d19eee58f1ad43c87d2cb65e271e21c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.068507Z","signature_b64":"a5UJwYxGNa+AI90wSpjsIeusaouIwL0+EijI21LBwj55M09Ek8lEMaUjBDCjhxlzi3SjZuJQbEy+7B9tXGUlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9812f7be06d574ac844373d5b1ac042151e7d2f4344bddf371eba5c2751f49ff","last_reissued_at":"2026-05-17T23:38:47.067451Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.067451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TripoSR produces a 3D mesh from one photo in under half a second by refining the LRM transformer design.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Letts, Christian Laforte, David Pankratz, Ding Liang, Dmitry Tochilkin, Varun Jampani, Yangguang Li, Yan-Pei Cao, Zexiang Liu, Zixuan Huang","submitted_at":"2024-03-04T16:00:56Z","abstract_excerpt":"This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0.5 seconds. Building upon the LRM network architecture, TripoSR integrates substantial improvements in data processing, model design, and training techniques. Evaluations on public datasets show that TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives. Released under the MIT license, TripoSR is intended to empower researchers, developers, a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"producing 3D mesh from a single image in under 0.5 seconds... TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the reported improvements in data processing, model design, and training techniques produce genuinely better generalization rather than fitting the specific evaluation datasets used.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TripoSR generates 3D meshes from single images in under 0.5 seconds using an improved transformer architecture over LRM.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TripoSR produces a 3D mesh from one photo in under half a second by refining the LRM transformer design.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"89d575cc297dbffa507c47f9086e5cabc182e0dcdc0a33586deff7b9a5d18114"},"source":{"id":"2403.02151","kind":"arxiv","version":1},"verdict":{"id":"24892418-1138-45de-acee-60179c85206c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T17:47:05.344727Z","strongest_claim":"producing 3D mesh from a single image in under 0.5 seconds... TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives.","one_line_summary":"TripoSR generates 3D meshes from single images in under 0.5 seconds using an improved transformer architecture over LRM.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the reported improvements in data processing, model design, and training techniques produce genuinely better generalization rather than fitting the specific evaluation datasets used.","pith_extraction_headline":"TripoSR produces a 3D mesh from one photo in under half a second by refining the LRM transformer design."},"references":{"count":35,"sample":[{"doi":"","year":2021,"title":"Emerg- ing properties in self-supervised vision transformers","work_id":"065afec2-aff4-4d04-b5dc-47af3a611897","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Efficient geometry-aware 3d generative adversarial networks","work_id":"14382871-c949-4538-acdb-46d2aeb9b7f2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Chan, Koki Nagano, Matthew A","work_id":"37608d54-b18d-4fdd-affd-12b3bbd8c9d8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Objaverse: A universe of annotated 3d objects","work_id":"fd98a821-2614-4cbf-b9d7-73f96cb6254d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Objaverse-xl: A universe of 10m+ 3d objects","work_id":"e7c55393-1f1c-4211-947a-6e61a92e53f6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":35,"snapshot_sha256":"807e5ada5af84eef91f3792da33c7a3a8acf8d2dd23e801ac1f22779190a33eb","internal_anchors":4},"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":"2403.02151","created_at":"2026-05-17T23:38:47.067569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02151v1","created_at":"2026-05-17T23:38:47.067569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02151","created_at":"2026-05-17T23:38:47.067569+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAJPPPQG2V2K","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAJPPPQG2V2KZBCD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAJPPPQG","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":27,"sample":[{"citing_arxiv_id":"2509.19102","citing_title":"FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16766","citing_title":"SVG360: Editable Multiview Vector Graphics from a Single SVG","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17916","citing_title":"PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18365","citing_title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2512.11988","citing_title":"CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":120,"is_internal_anchor":true},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":206,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14984","citing_title":"Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image","ref_index":99,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23018","citing_title":"AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13293","citing_title":"Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":206,"is_internal_anchor":true},{"citing_arxiv_id":"2404.07191","citing_title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06311","citing_title":"Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23018","citing_title":"AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00804","citing_title":"Prop-Chromeleon: Adaptive Haptic Props in Mixed Reality through Generative Artificial Intelligence","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12309","citing_title":"Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08746","citing_title":"AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08610","citing_title":"A Semi-Automated Framework for 3D Reconstruction of Medieval Manuscript Miniatures","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":118,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05510","citing_title":"Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF","json":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF.json","graph_json":"https://pith.science/api/pith-number/TAJPPPQG2V2KZBCDOPK3DLAEEF/graph.json","events_json":"https://pith.science/api/pith-number/TAJPPPQG2V2KZBCDOPK3DLAEEF/events.json","paper":"https://pith.science/paper/TAJPPPQG"},"agent_actions":{"view_html":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF","download_json":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF.json","view_paper":"https://pith.science/paper/TAJPPPQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02151&json=true","fetch_graph":"https://pith.science/api/pith-number/TAJPPPQG2V2KZBCDOPK3DLAEEF/graph.json","fetch_events":"https://pith.science/api/pith-number/TAJPPPQG2V2KZBCDOPK3DLAEEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF/action/storage_attestation","attest_author":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF/action/author_attestation","sign_citation":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF/action/citation_signature","submit_replication":"https://pith.science/pith/TAJPPPQG2V2KZBCDOPK3DLAEEF/action/replication_record"}},"created_at":"2026-05-17T23:38:47.067569+00:00","updated_at":"2026-05-17T23:38:47.067569+00:00"}