{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GXK4QAKV3N7ZLPKTLSEAGQI3XI","short_pith_number":"pith:GXK4QAKV","schema_version":"1.0","canonical_sha256":"35d5c80155db7f95bd535c8803411bba3bf073028d52efff3e4be8acd257bc4e","source":{"kind":"arxiv","id":"2407.04237","version":4},"attestation_state":"computed","paper":{"title":"GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chuan Guo, Juwei Lu, Li Cheng, Peng Dai, Songcen Xu, Xiaofeng Wu, Xinxin Zuo, Yilin Wang, Youliang Yan, Yuxuan Mu","submitted_at":"2024-07-05T03:43:08Z","abstract_excerpt":"We present GSD, a diffusion model approach based on Gaussian Splatting (GS) representation for 3D object reconstruction from a single view. Prior works suffer from inconsistent 3D geometry or mediocre rendering quality due to improper representations. We take a step towards resolving these shortcomings by utilizing the recent state-of-the-art 3D explicit representation, Gaussian Splatting, and an unconditional diffusion model. This model learns to generate 3D objects represented by sets of GS ellipsoids. With these strong generative 3D priors, though learning unconditionally, the diffusion mod"},"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":"2407.04237","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T03:43:08Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"378d5d73cbdb6089f6a585f0e90c33f0965e3a030fefe1bdfe2168b949297ba3","abstract_canon_sha256":"b0fd9e6e79c0c41a8e58380b8c56940f67bc48a7a5476b9323ed61661bb8bc5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:56.709248Z","signature_b64":"49Yv4QQKK0MC2Q1fUUCR1jFy+c4/s3Dufha6nA+C8OlyIE2mEadsTXYo78QuBzPcq/TzZeNwQ6tW6smyHD8gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d5c80155db7f95bd535c8803411bba3bf073028d52efff3e4be8acd257bc4e","last_reissued_at":"2026-07-05T09:27:56.708762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:56.708762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chuan Guo, Juwei Lu, Li Cheng, Peng Dai, Songcen Xu, Xiaofeng Wu, Xinxin Zuo, Yilin Wang, Youliang Yan, Yuxuan Mu","submitted_at":"2024-07-05T03:43:08Z","abstract_excerpt":"We present GSD, a diffusion model approach based on Gaussian Splatting (GS) representation for 3D object reconstruction from a single view. Prior works suffer from inconsistent 3D geometry or mediocre rendering quality due to improper representations. We take a step towards resolving these shortcomings by utilizing the recent state-of-the-art 3D explicit representation, Gaussian Splatting, and an unconditional diffusion model. This model learns to generate 3D objects represented by sets of GS ellipsoids. With these strong generative 3D priors, though learning unconditionally, the diffusion mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04237","kind":"arxiv","version":4},"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/2407.04237/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":"2407.04237","created_at":"2026-07-05T09:27:56.708817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04237v4","created_at":"2026-07-05T09:27:56.708817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04237","created_at":"2026-07-05T09:27:56.708817+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXK4QAKV3N7Z","created_at":"2026-07-05T09:27:56.708817+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXK4QAKV3N7ZLPKT","created_at":"2026-07-05T09:27:56.708817+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXK4QAKV","created_at":"2026-07-05T09:27:56.708817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24180","citing_title":"Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13364","citing_title":"VideoMDM: Towards 3D Human Motion Generation From 2D Supervision","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI","json":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI.json","graph_json":"https://pith.science/api/pith-number/GXK4QAKV3N7ZLPKTLSEAGQI3XI/graph.json","events_json":"https://pith.science/api/pith-number/GXK4QAKV3N7ZLPKTLSEAGQI3XI/events.json","paper":"https://pith.science/paper/GXK4QAKV"},"agent_actions":{"view_html":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI","download_json":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI.json","view_paper":"https://pith.science/paper/GXK4QAKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04237&json=true","fetch_graph":"https://pith.science/api/pith-number/GXK4QAKV3N7ZLPKTLSEAGQI3XI/graph.json","fetch_events":"https://pith.science/api/pith-number/GXK4QAKV3N7ZLPKTLSEAGQI3XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI/action/storage_attestation","attest_author":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI/action/author_attestation","sign_citation":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI/action/citation_signature","submit_replication":"https://pith.science/pith/GXK4QAKV3N7ZLPKTLSEAGQI3XI/action/replication_record"}},"created_at":"2026-07-05T09:27:56.708817+00:00","updated_at":"2026-07-05T09:27:56.708817+00:00"}