{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BG3WJPJWDXFIKJH4YIDUXTYUDX","short_pith_number":"pith:BG3WJPJW","schema_version":"1.0","canonical_sha256":"09b764bd361dca8524fcc2074bcf141dc24455f6b14e29d0e91d2cbd05a65012","source":{"kind":"arxiv","id":"2504.01960","version":1},"attestation_state":"computed","paper":{"title":"Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ben Southall, Bogdan Matei, Kshitij Minhas, Niluthpol Chowdhury Mithun, Qiao Wang, Rakesh Kumar, Stephan Mandt, Supun Samarasekera, Tuan Pham","submitted_at":"2025-04-02T17:59:46Z","abstract_excerpt":"Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. However, these methods struggle in large-scale, unconstrained environments where sparse and uneven input coverage, transient occlusions, appearance variability, and inconsistent camera settings lead to degraded quality. We propose GS-Diff, a novel 3DGS framework guided by a multi-view diffusion model to address these limitations. By generating pseudo-observations conditioned on multi-view inputs, our method transforms un"},"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":"2504.01960","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T17:59:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5aaea25d31846aade63c0083603c02d10e9c400845cf70366864aa38ecd7be1c","abstract_canon_sha256":"b33b317bd56ba15feeda7697bbb248a5e2ecc176bf81a02f0a1c8a4337ca656f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:32.354027Z","signature_b64":"Grh+twGedBHhRNeV06aHqfKEUr7LTUlkGaMuWj3CHCmIQgByaA+bbag/xCXfBWsCrDbcBpm9VELHrcp4sORIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09b764bd361dca8524fcc2074bcf141dc24455f6b14e29d0e91d2cbd05a65012","last_reissued_at":"2026-07-05T10:43:32.353539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:32.353539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ben Southall, Bogdan Matei, Kshitij Minhas, Niluthpol Chowdhury Mithun, Qiao Wang, Rakesh Kumar, Stephan Mandt, Supun Samarasekera, Tuan Pham","submitted_at":"2025-04-02T17:59:46Z","abstract_excerpt":"Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. However, these methods struggle in large-scale, unconstrained environments where sparse and uneven input coverage, transient occlusions, appearance variability, and inconsistent camera settings lead to degraded quality. We propose GS-Diff, a novel 3DGS framework guided by a multi-view diffusion model to address these limitations. By generating pseudo-observations conditioned on multi-view inputs, our method transforms un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01960","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/2504.01960/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":"2504.01960","created_at":"2026-07-05T10:43:32.353598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01960v1","created_at":"2026-07-05T10:43:32.353598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01960","created_at":"2026-07-05T10:43:32.353598+00:00"},{"alias_kind":"pith_short_12","alias_value":"BG3WJPJWDXFI","created_at":"2026-07-05T10:43:32.353598+00:00"},{"alias_kind":"pith_short_16","alias_value":"BG3WJPJWDXFIKJH4","created_at":"2026-07-05T10:43:32.353598+00:00"},{"alias_kind":"pith_short_8","alias_value":"BG3WJPJW","created_at":"2026-07-05T10:43:32.353598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13416","citing_title":"DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX","json":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX.json","graph_json":"https://pith.science/api/pith-number/BG3WJPJWDXFIKJH4YIDUXTYUDX/graph.json","events_json":"https://pith.science/api/pith-number/BG3WJPJWDXFIKJH4YIDUXTYUDX/events.json","paper":"https://pith.science/paper/BG3WJPJW"},"agent_actions":{"view_html":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX","download_json":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX.json","view_paper":"https://pith.science/paper/BG3WJPJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01960&json=true","fetch_graph":"https://pith.science/api/pith-number/BG3WJPJWDXFIKJH4YIDUXTYUDX/graph.json","fetch_events":"https://pith.science/api/pith-number/BG3WJPJWDXFIKJH4YIDUXTYUDX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX/action/storage_attestation","attest_author":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX/action/author_attestation","sign_citation":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX/action/citation_signature","submit_replication":"https://pith.science/pith/BG3WJPJWDXFIKJH4YIDUXTYUDX/action/replication_record"}},"created_at":"2026-07-05T10:43:32.353598+00:00","updated_at":"2026-07-05T10:43:32.353598+00:00"}