{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IKRCHNDERJX7FDGIREXD3YTLOJ","short_pith_number":"pith:IKRCHNDE","schema_version":"1.0","canonical_sha256":"42a223b4648a6ff28cc8892e3de26b725573dae93cea4fb1a172f2bad85523bd","source":{"kind":"arxiv","id":"2210.15663","version":3},"attestation_state":"computed","paper":{"title":"Deep Generative Models on 3D Representations: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Sida Peng, Yinghao Xu, Yiyi Liao, Yujun Shen, Zifan Shi","submitted_at":"2022-10-27T17:59:50Z","abstract_excerpt":"Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models (DMs), have progressed remarkably in synthesizing 2D images. Recently, researchers started to shift focus from 2D to 3D space, considering that 3D data is more closely aligned with our physical world and holds immense practical potential. However, unlike 2D images, which possess an inherent and efficient representation (\\textit{i.e.}, a pix"},"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":"2210.15663","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T17:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"7bb52ee5c1efa0416e8287fb683d540913ee6ca4fc9f0df5fd6163e2f649a89b","abstract_canon_sha256":"d204b75f72662e426393f9ad97d515d5901644b1e37b697006d5e4387b52a21d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:12.929136Z","signature_b64":"Yc26GOpWMOhFL6ULmJJals2RXnPVYAN/XiCgjHtG24r8Dw2j6aRwM+cbiyFrabFf0H7XKJHAozS7BgvciPSECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a223b4648a6ff28cc8892e3de26b725573dae93cea4fb1a172f2bad85523bd","last_reissued_at":"2026-07-05T06:45:12.928651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:12.928651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Generative Models on 3D Representations: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Sida Peng, Yinghao Xu, Yiyi Liao, Yujun Shen, Zifan Shi","submitted_at":"2022-10-27T17:59:50Z","abstract_excerpt":"Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models (DMs), have progressed remarkably in synthesizing 2D images. Recently, researchers started to shift focus from 2D to 3D space, considering that 3D data is more closely aligned with our physical world and holds immense practical potential. However, unlike 2D images, which possess an inherent and efficient representation (\\textit{i.e.}, a pix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15663","kind":"arxiv","version":3},"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/2210.15663/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":"2210.15663","created_at":"2026-07-05T06:45:12.928710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15663v3","created_at":"2026-07-05T06:45:12.928710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15663","created_at":"2026-07-05T06:45:12.928710+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKRCHNDERJX7","created_at":"2026-07-05T06:45:12.928710+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKRCHNDERJX7FDGI","created_at":"2026-07-05T06:45:12.928710+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKRCHNDE","created_at":"2026-07-05T06:45:12.928710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27305","citing_title":"Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06624","citing_title":"Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2403.02151","citing_title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09688","citing_title":"Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ","json":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ.json","graph_json":"https://pith.science/api/pith-number/IKRCHNDERJX7FDGIREXD3YTLOJ/graph.json","events_json":"https://pith.science/api/pith-number/IKRCHNDERJX7FDGIREXD3YTLOJ/events.json","paper":"https://pith.science/paper/IKRCHNDE"},"agent_actions":{"view_html":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ","download_json":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ.json","view_paper":"https://pith.science/paper/IKRCHNDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15663&json=true","fetch_graph":"https://pith.science/api/pith-number/IKRCHNDERJX7FDGIREXD3YTLOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IKRCHNDERJX7FDGIREXD3YTLOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ/action/storage_attestation","attest_author":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ/action/author_attestation","sign_citation":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ/action/citation_signature","submit_replication":"https://pith.science/pith/IKRCHNDERJX7FDGIREXD3YTLOJ/action/replication_record"}},"created_at":"2026-07-05T06:45:12.928710+00:00","updated_at":"2026-07-05T06:45:12.928710+00:00"}