{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TSDEFTVC7FH2PYPEG4YAUOCLJ3","short_pith_number":"pith:TSDEFTVC","schema_version":"1.0","canonical_sha256":"9c8642cea2f94fa7e1e437300a384b4ee1bdbf65bfcacc973803bce79bb597a2","source":{"kind":"arxiv","id":"2403.13524","version":1},"attestation_state":"computed","paper":{"title":"Compress3D: a Compressed Latent Space for 3D Generation from a Single Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Lei Zhang, Tianyu Yang, Xi Zhao, Yu Li","submitted_at":"2024-03-20T11:51:04Z","abstract_excerpt":"3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which encodes 3D models into a compact triplane latent space to effectively compress both the 3D geometry and texture information. Within the autoencoder framework, we introduce a 3D-aware cross-attention mechanism, which utilizes low-resolution latent representations to query features from a high-resolution 3D feature volume, thereby enhancing the representation capacity of the latent space. Subsequent"},"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":"2403.13524","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T11:51:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a4239a5e0f95459f469db5e88b1479183f5353a397021a3447498b291f4635f5","abstract_canon_sha256":"e86f14f080609182cd5f872f9128a7870dba92a5722aa043f68a4bbf4c71ff9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:37.891154Z","signature_b64":"JO4AHKm8hITZMgEADPCKdGzDkX8VkbrQRb4BGtZcLzkTQImjqFWlg8z+Pn5hoSdkMgWkAjw98uRVa3wPPeL7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c8642cea2f94fa7e1e437300a384b4ee1bdbf65bfcacc973803bce79bb597a2","last_reissued_at":"2026-07-05T07:58:37.890637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:37.890637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compress3D: a Compressed Latent Space for 3D Generation from a Single Image","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Lei Zhang, Tianyu Yang, Xi Zhao, Yu Li","submitted_at":"2024-03-20T11:51:04Z","abstract_excerpt":"3D generation has witnessed significant advancements, yet efficiently producing high-quality 3D assets from a single image remains challenging. In this paper, we present a triplane autoencoder, which encodes 3D models into a compact triplane latent space to effectively compress both the 3D geometry and texture information. Within the autoencoder framework, we introduce a 3D-aware cross-attention mechanism, which utilizes low-resolution latent representations to query features from a high-resolution 3D feature volume, thereby enhancing the representation capacity of the latent space. Subsequent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13524","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/2403.13524/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":"2403.13524","created_at":"2026-07-05T07:58:37.890695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13524v1","created_at":"2026-07-05T07:58:37.890695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13524","created_at":"2026-07-05T07:58:37.890695+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSDEFTVC7FH2","created_at":"2026-07-05T07:58:37.890695+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSDEFTVC7FH2PYPE","created_at":"2026-07-05T07:58:37.890695+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSDEFTVC","created_at":"2026-07-05T07:58:37.890695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":133,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3","json":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3.json","graph_json":"https://pith.science/api/pith-number/TSDEFTVC7FH2PYPEG4YAUOCLJ3/graph.json","events_json":"https://pith.science/api/pith-number/TSDEFTVC7FH2PYPEG4YAUOCLJ3/events.json","paper":"https://pith.science/paper/TSDEFTVC"},"agent_actions":{"view_html":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3","download_json":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3.json","view_paper":"https://pith.science/paper/TSDEFTVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13524&json=true","fetch_graph":"https://pith.science/api/pith-number/TSDEFTVC7FH2PYPEG4YAUOCLJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/TSDEFTVC7FH2PYPEG4YAUOCLJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3/action/storage_attestation","attest_author":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3/action/author_attestation","sign_citation":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3/action/citation_signature","submit_replication":"https://pith.science/pith/TSDEFTVC7FH2PYPEG4YAUOCLJ3/action/replication_record"}},"created_at":"2026-07-05T07:58:37.890695+00:00","updated_at":"2026-07-05T07:58:37.890695+00:00"}