{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCBRUKEHMRENQV6K4EPAKUOVXT","short_pith_number":"pith:YCBRUKEH","schema_version":"1.0","canonical_sha256":"c0831a28876448d857cae11e0551d5bcd1fb29b67167fb943fd9c18ae35bdc62","source":{"kind":"arxiv","id":"2508.21542","version":1},"attestation_state":"computed","paper":{"title":"Complete Gaussian Splats from a Single Image with Denoising Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniyar Turmukhambetov, Michael Firman, Mohamed Sayed, Sara Vicente, Steven L. Waslander, Ziwei Liao","submitted_at":"2025-08-29T11:55:47Z","abstract_excerpt":"Gaussian splatting typically requires dense observations of the scene and can fail to reconstruct occluded and unobserved areas. We propose a latent diffusion model to reconstruct a complete 3D scene with Gaussian splats, including the occluded parts, from only a single image during inference. Completing the unobserved surfaces of a scene is challenging due to the ambiguity of the plausible surfaces. Conventional methods use a regression-based formulation to predict a single \"mode\" for occluded and out-of-frustum surfaces, leading to blurriness, implausibility, and failure to capture multiple "},"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":"2508.21542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T11:55:47Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"95e1ba379807d6a370596a8098b50768552bef21d416e8f09869eeb7a6f79b90","abstract_canon_sha256":"cc8ebc849a7c5f7919dc025d49b35e079674eed9788cbdd387e2556cdf2140ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:36.409437Z","signature_b64":"nXx6uDiU2fC8+bb6HT2U9egRUFiPY3sNcvB8rZbyhzr4bMSldStnZR4k12KMQ7ewEh18emlCgGJjos/lyQ9WAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0831a28876448d857cae11e0551d5bcd1fb29b67167fb943fd9c18ae35bdc62","last_reissued_at":"2026-07-05T12:01:36.408939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:36.408939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complete Gaussian Splats from a Single Image with Denoising Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Daniyar Turmukhambetov, Michael Firman, Mohamed Sayed, Sara Vicente, Steven L. Waslander, Ziwei Liao","submitted_at":"2025-08-29T11:55:47Z","abstract_excerpt":"Gaussian splatting typically requires dense observations of the scene and can fail to reconstruct occluded and unobserved areas. We propose a latent diffusion model to reconstruct a complete 3D scene with Gaussian splats, including the occluded parts, from only a single image during inference. Completing the unobserved surfaces of a scene is challenging due to the ambiguity of the plausible surfaces. Conventional methods use a regression-based formulation to predict a single \"mode\" for occluded and out-of-frustum surfaces, leading to blurriness, implausibility, and failure to capture multiple "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21542","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/2508.21542/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":"2508.21542","created_at":"2026-07-05T12:01:36.408999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21542v1","created_at":"2026-07-05T12:01:36.408999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21542","created_at":"2026-07-05T12:01:36.408999+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCBRUKEHMREN","created_at":"2026-07-05T12:01:36.408999+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCBRUKEHMRENQV6K","created_at":"2026-07-05T12:01:36.408999+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCBRUKEH","created_at":"2026-07-05T12:01:36.408999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT","json":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT.json","graph_json":"https://pith.science/api/pith-number/YCBRUKEHMRENQV6K4EPAKUOVXT/graph.json","events_json":"https://pith.science/api/pith-number/YCBRUKEHMRENQV6K4EPAKUOVXT/events.json","paper":"https://pith.science/paper/YCBRUKEH"},"agent_actions":{"view_html":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT","download_json":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT.json","view_paper":"https://pith.science/paper/YCBRUKEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21542&json=true","fetch_graph":"https://pith.science/api/pith-number/YCBRUKEHMRENQV6K4EPAKUOVXT/graph.json","fetch_events":"https://pith.science/api/pith-number/YCBRUKEHMRENQV6K4EPAKUOVXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT/action/storage_attestation","attest_author":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT/action/author_attestation","sign_citation":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT/action/citation_signature","submit_replication":"https://pith.science/pith/YCBRUKEHMRENQV6K4EPAKUOVXT/action/replication_record"}},"created_at":"2026-07-05T12:01:36.408999+00:00","updated_at":"2026-07-05T12:01:36.408999+00:00"}