{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K5IILP4GJIMRKH6U2VR5MDZOG6","short_pith_number":"pith:K5IILP4G","schema_version":"1.0","canonical_sha256":"575085bf864a19151fd4d563d60f2e379960ac401e8864a5fa0750381f61077c","source":{"kind":"arxiv","id":"2408.13055","version":3},"attestation_state":"computed","paper":{"title":"Atlas Gaussians Diffusion for 3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Georgios Pavlakos, Haitao Yang, Hanwen Jiang, Qixing Huang, Yuan Dong","submitted_at":"2024-08-23T13:27:27Z","abstract_excerpt":"Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidelity and efficient representation that links the latent space and the 3D space. In this paper, we introduce Atlas Gaussians, a novel representation for feed-forward native 3D generation. Atlas Gaussians represent a shape as the union of local patches, and each patch can decode 3D Gaussians. We parameterize a patch as a sequence of feature vectors and design a learnable function to decode 3D Gaussians from the feature "},"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":"2408.13055","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T13:27:27Z","cross_cats_sorted":[],"title_canon_sha256":"300cbe052a50c681af361dac15108f8222643d4d3213ea01a0e9bf66d8f4b33b","abstract_canon_sha256":"22bc5bd8e6a367ad22c35dd4f666a2ecf2b62d291f771751f7c0ba0c8cc30c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:38.163533Z","signature_b64":"Lu8O3iTwhN8xpbJBEuc9ZuomxpPl9mzhE5pR1Mpu7vfL+P62mJ4I6EOZXtxD2lrj/fsb8t9/s648ef8Ul+WoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"575085bf864a19151fd4d563d60f2e379960ac401e8864a5fa0750381f61077c","last_reissued_at":"2026-07-05T10:46:38.163084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:38.163084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Atlas Gaussians Diffusion for 3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Georgios Pavlakos, Haitao Yang, Hanwen Jiang, Qixing Huang, Yuan Dong","submitted_at":"2024-08-23T13:27:27Z","abstract_excerpt":"Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidelity and efficient representation that links the latent space and the 3D space. In this paper, we introduce Atlas Gaussians, a novel representation for feed-forward native 3D generation. Atlas Gaussians represent a shape as the union of local patches, and each patch can decode 3D Gaussians. We parameterize a patch as a sequence of feature vectors and design a learnable function to decode 3D Gaussians from the feature "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13055","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/2408.13055/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":"2408.13055","created_at":"2026-07-05T10:46:38.163134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13055v3","created_at":"2026-07-05T10:46:38.163134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13055","created_at":"2026-07-05T10:46:38.163134+00:00"},{"alias_kind":"pith_short_12","alias_value":"K5IILP4GJIMR","created_at":"2026-07-05T10:46:38.163134+00:00"},{"alias_kind":"pith_short_16","alias_value":"K5IILP4GJIMRKH6U","created_at":"2026-07-05T10:46:38.163134+00:00"},{"alias_kind":"pith_short_8","alias_value":"K5IILP4G","created_at":"2026-07-05T10:46:38.163134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16355","citing_title":"Generative 3D Gaussians with Learned Density Control","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05182","citing_title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6","json":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6.json","graph_json":"https://pith.science/api/pith-number/K5IILP4GJIMRKH6U2VR5MDZOG6/graph.json","events_json":"https://pith.science/api/pith-number/K5IILP4GJIMRKH6U2VR5MDZOG6/events.json","paper":"https://pith.science/paper/K5IILP4G"},"agent_actions":{"view_html":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6","download_json":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6.json","view_paper":"https://pith.science/paper/K5IILP4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13055&json=true","fetch_graph":"https://pith.science/api/pith-number/K5IILP4GJIMRKH6U2VR5MDZOG6/graph.json","fetch_events":"https://pith.science/api/pith-number/K5IILP4GJIMRKH6U2VR5MDZOG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6/action/storage_attestation","attest_author":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6/action/author_attestation","sign_citation":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6/action/citation_signature","submit_replication":"https://pith.science/pith/K5IILP4GJIMRKH6U2VR5MDZOG6/action/replication_record"}},"created_at":"2026-07-05T10:46:38.163134+00:00","updated_at":"2026-07-05T10:46:38.163134+00:00"}