{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:POSYM3RBQOZTZCZSHVVULBYYP6","short_pith_number":"pith:POSYM3RB","schema_version":"1.0","canonical_sha256":"7ba5866e2183b33c8b323d6b4587187faab386266283d2223ab42b2030bb29a6","source":{"kind":"arxiv","id":"2305.15399","version":2},"attestation_state":"computed","paper":{"title":"Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Changxi Zheng, Rundi Wu, Ruoshi Liu","submitted_at":"2023-05-24T17:57:15Z","abstract_excerpt":"Synthesizing novel 3D models that resemble the input example has long been pursued by graphics artists and machine learning researchers. In this paper, we present Sin3DM, a diffusion model that learns the internal patch distribution from a single 3D textured shape and generates high-quality variations with fine geometry and texture details. Training a diffusion model directly in 3D would induce large memory and computational cost. Therefore, we first compress the input into a lower-dimensional latent space and then train a diffusion model on it. Specifically, we encode the input 3D textured sh"},"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":"2305.15399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T17:57:15Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"099eaad00003385a20989f1cf42d99c4d0f7707184bec1bad94fd6f4342f6a57","abstract_canon_sha256":"9a7d8847006efeedad593172de21142e28d829392d2ea4c46cd1c29ccae2f5fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:25.204944Z","signature_b64":"RiIeMwQ8IfoQVYgaKjjstcfd57AYhMCMjkQLAyYCgWivubMtycNZz2wnmGNAE08bgvnikqBlyIDjXkaonVuQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ba5866e2183b33c8b323d6b4587187faab386266283d2223ab42b2030bb29a6","last_reissued_at":"2026-07-05T07:47:25.204504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:25.204504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Carl Vondrick, Changxi Zheng, Rundi Wu, Ruoshi Liu","submitted_at":"2023-05-24T17:57:15Z","abstract_excerpt":"Synthesizing novel 3D models that resemble the input example has long been pursued by graphics artists and machine learning researchers. In this paper, we present Sin3DM, a diffusion model that learns the internal patch distribution from a single 3D textured shape and generates high-quality variations with fine geometry and texture details. Training a diffusion model directly in 3D would induce large memory and computational cost. Therefore, we first compress the input into a lower-dimensional latent space and then train a diffusion model on it. Specifically, we encode the input 3D textured sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15399","kind":"arxiv","version":2},"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/2305.15399/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":"2305.15399","created_at":"2026-07-05T07:47:25.204560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15399v2","created_at":"2026-07-05T07:47:25.204560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15399","created_at":"2026-07-05T07:47:25.204560+00:00"},{"alias_kind":"pith_short_12","alias_value":"POSYM3RBQOZT","created_at":"2026-07-05T07:47:25.204560+00:00"},{"alias_kind":"pith_short_16","alias_value":"POSYM3RBQOZTZCZS","created_at":"2026-07-05T07:47:25.204560+00:00"},{"alias_kind":"pith_short_8","alias_value":"POSYM3RB","created_at":"2026-07-05T07:47:25.204560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23489","citing_title":"MeshFlow: Mesh Generation with Equivariant Flow Matching","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08957","citing_title":"Rethinking 3D Shape Generation: Diffusion over Superquadrics","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20093","citing_title":"FurnSet: Exploiting Repeats for 3D Scene Reconstruction","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12575","citing_title":"StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6","json":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6.json","graph_json":"https://pith.science/api/pith-number/POSYM3RBQOZTZCZSHVVULBYYP6/graph.json","events_json":"https://pith.science/api/pith-number/POSYM3RBQOZTZCZSHVVULBYYP6/events.json","paper":"https://pith.science/paper/POSYM3RB"},"agent_actions":{"view_html":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6","download_json":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6.json","view_paper":"https://pith.science/paper/POSYM3RB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15399&json=true","fetch_graph":"https://pith.science/api/pith-number/POSYM3RBQOZTZCZSHVVULBYYP6/graph.json","fetch_events":"https://pith.science/api/pith-number/POSYM3RBQOZTZCZSHVVULBYYP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6/action/storage_attestation","attest_author":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6/action/author_attestation","sign_citation":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6/action/citation_signature","submit_replication":"https://pith.science/pith/POSYM3RBQOZTZCZSHVVULBYYP6/action/replication_record"}},"created_at":"2026-07-05T07:47:25.204560+00:00","updated_at":"2026-07-05T07:47:25.204560+00:00"}