{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PJ3MDSJOPUMCHMTYZAVJN6KRL6","short_pith_number":"pith:PJ3MDSJO","schema_version":"1.0","canonical_sha256":"7a76c1c92e7d1823b278c82a96f9515f8adabb6fbe0e4c1216653fa68ba34c41","source":{"kind":"arxiv","id":"2212.04493","version":2},"attestation_state":"computed","paper":{"title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Schwing, Hsin-Ying Lee, Liangyan Gui, Sergey Tulyakov, Yen-Chi Cheng","submitted_at":"2022-12-08T18:59:05Z","abstract_excerpt":"In this work, we present a novel framework built to simplify 3D asset generation for amateur users. To enable interactive generation, our method supports a variety of input modalities that can be easily provided by a human, including images, text, partially observed shapes and combinations of these, further allowing to adjust the strength of each input. At the core of our approach is an encoder-decoder, compressing 3D shapes into a compact latent representation, upon which a diffusion model is learned. To enable a variety of multi-modal inputs, we employ task-specific encoders with dropout fol"},"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":"2212.04493","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19968fa66914866a122ed8ef47f964d7fe1507cddcb7c9bddfa1dd6b2eec31ec","abstract_canon_sha256":"6d8d99a42b580f212fe489cf046e036d7c4975a3ef21b6262f7fe885ea3fa223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:35.182957Z","signature_b64":"BtYDBTp0VutggtlV8b5VaF/4fly5MTDHuvW/6xQR8ZoqIjdDsVsjI7rR55QIwgDwBplOXHkZeiNwN49bcPkoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a76c1c92e7d1823b278c82a96f9515f8adabb6fbe0e4c1216653fa68ba34c41","last_reissued_at":"2026-07-05T05:53:35.182475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:35.182475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Schwing, Hsin-Ying Lee, Liangyan Gui, Sergey Tulyakov, Yen-Chi Cheng","submitted_at":"2022-12-08T18:59:05Z","abstract_excerpt":"In this work, we present a novel framework built to simplify 3D asset generation for amateur users. To enable interactive generation, our method supports a variety of input modalities that can be easily provided by a human, including images, text, partially observed shapes and combinations of these, further allowing to adjust the strength of each input. At the core of our approach is an encoder-decoder, compressing 3D shapes into a compact latent representation, upon which a diffusion model is learned. To enable a variety of multi-modal inputs, we employ task-specific encoders with dropout fol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04493","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/2212.04493/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":"2212.04493","created_at":"2026-07-05T05:53:35.182534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04493v2","created_at":"2026-07-05T05:53:35.182534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04493","created_at":"2026-07-05T05:53:35.182534+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ3MDSJOPUMC","created_at":"2026-07-05T05:53:35.182534+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ3MDSJOPUMCHMTY","created_at":"2026-07-05T05:53:35.182534+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ3MDSJO","created_at":"2026-07-05T05:53:35.182534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6","json":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6.json","graph_json":"https://pith.science/api/pith-number/PJ3MDSJOPUMCHMTYZAVJN6KRL6/graph.json","events_json":"https://pith.science/api/pith-number/PJ3MDSJOPUMCHMTYZAVJN6KRL6/events.json","paper":"https://pith.science/paper/PJ3MDSJO"},"agent_actions":{"view_html":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6","download_json":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6.json","view_paper":"https://pith.science/paper/PJ3MDSJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04493&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ3MDSJOPUMCHMTYZAVJN6KRL6/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ3MDSJOPUMCHMTYZAVJN6KRL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6/action/storage_attestation","attest_author":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6/action/author_attestation","sign_citation":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6/action/citation_signature","submit_replication":"https://pith.science/pith/PJ3MDSJOPUMCHMTYZAVJN6KRL6/action/replication_record"}},"created_at":"2026-07-05T05:53:35.182534+00:00","updated_at":"2026-07-05T05:53:35.182534+00:00"}