{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QRHHAM2FPCF5HA63PDF2M4YOSP","short_pith_number":"pith:QRHHAM2F","schema_version":"1.0","canonical_sha256":"844e703345788bd383db78cba6730e93ef7974a63d201a67cebb6cffc6bb7ee7","source":{"kind":"arxiv","id":"2307.05445","version":1},"attestation_state":"computed","paper":{"title":"AutoDecoding Latent 3D Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Chaoyang Wang, Evangelos Ntavelis, Kyle Olszewski, Luc Van Gool, Sergey Tulyakov","submitted_at":"2023-07-07T17:59:14Z","abstract_excerpt":"We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations to learn a 3D diffusion from 2D images or monocular videos of rigid or articulated objects. Our approach is flexible enough to "},"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":"2307.05445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-07T17:59:14Z","cross_cats_sorted":[],"title_canon_sha256":"7d572649ffd0ca0b235b872b6beb5cd9c4c8b2b90297900740c62d31fac887d0","abstract_canon_sha256":"2d42b9beb11f8c735fda241b04cd8d6ef6d7c3a17692656fd590fd2564a64997"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:57.921814Z","signature_b64":"7tH/H3CQnNBOQ/26TqlMLsJQABir/um9yKLGUREKKjMpxrJ++0sgobGuTaJZuL6D77k+VQ/UQtLu2UkbrnwiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"844e703345788bd383db78cba6730e93ef7974a63d201a67cebb6cffc6bb7ee7","last_reissued_at":"2026-07-05T06:29:57.921278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:57.921278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoDecoding Latent 3D Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Chaoyang Wang, Evangelos Ntavelis, Kyle Olszewski, Luc Van Gool, Sergey Tulyakov","submitted_at":"2023-07-07T17:59:14Z","abstract_excerpt":"We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be decoded into a volumetric representation for rendering view-consistent appearance and geometry. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations to learn a 3D diffusion from 2D images or monocular videos of rigid or articulated objects. Our approach is flexible enough to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05445","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/2307.05445/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":"2307.05445","created_at":"2026-07-05T06:29:57.921340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05445v1","created_at":"2026-07-05T06:29:57.921340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05445","created_at":"2026-07-05T06:29:57.921340+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRHHAM2FPCF5","created_at":"2026-07-05T06:29:57.921340+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRHHAM2FPCF5HA63","created_at":"2026-07-05T06:29:57.921340+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRHHAM2F","created_at":"2026-07-05T06:29:57.921340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.16764","citing_title":"BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16653","citing_title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","ref_index":131,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP","json":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP.json","graph_json":"https://pith.science/api/pith-number/QRHHAM2FPCF5HA63PDF2M4YOSP/graph.json","events_json":"https://pith.science/api/pith-number/QRHHAM2FPCF5HA63PDF2M4YOSP/events.json","paper":"https://pith.science/paper/QRHHAM2F"},"agent_actions":{"view_html":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP","download_json":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP.json","view_paper":"https://pith.science/paper/QRHHAM2F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05445&json=true","fetch_graph":"https://pith.science/api/pith-number/QRHHAM2FPCF5HA63PDF2M4YOSP/graph.json","fetch_events":"https://pith.science/api/pith-number/QRHHAM2FPCF5HA63PDF2M4YOSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP/action/storage_attestation","attest_author":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP/action/author_attestation","sign_citation":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP/action/citation_signature","submit_replication":"https://pith.science/pith/QRHHAM2FPCF5HA63PDF2M4YOSP/action/replication_record"}},"created_at":"2026-07-05T06:29:57.921340+00:00","updated_at":"2026-07-05T06:29:57.921340+00:00"}