{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQ62PGAWZHT6IM2XSJ4NLPA2MN","short_pith_number":"pith:WQ62PGAW","schema_version":"1.0","canonical_sha256":"b43da79816c9e7e433579278d5bc1a6363bd0c8f01fe9c226b56a80212e59200","source":{"kind":"arxiv","id":"2404.11613","version":1},"attestation_state":"computed","paper":{"title":"InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ouyang, Jie Xiao, Kai Zhu, Ka Leong Cheng, Nan Xue, Qiuyu Wang, Yang Cao, Yujun Shen, Yu Liu, Zhiheng Liu","submitted_at":"2024-04-17T17:59:53Z","abstract_excerpt":"3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion"},"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":"2404.11613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-17T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"338acca486138d61fe2ea59d23034f2ba818d6f1cf19678aa7541b4ad22ec836","abstract_canon_sha256":"17a015de7b025f0f37232bcd978d2ff23773c0b813a36642ed19e62d2feb6574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:10.996869Z","signature_b64":"R5LkZFMYMPoV30lT0yldZD3LV/AN/dYqEoEPD/jQXw280bPYWmGCLu9kI1WNPoK05G1TjOWKfyO3dQCHSbjFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43da79816c9e7e433579278d5bc1a6363bd0c8f01fe9c226b56a80212e59200","last_reissued_at":"2026-07-05T08:09:10.996414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:10.996414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Ouyang, Jie Xiao, Kai Zhu, Ka Leong Cheng, Nan Xue, Qiuyu Wang, Yang Cao, Yujun Shen, Yu Liu, Zhiheng Liu","submitted_at":"2024-04-17T17:59:53Z","abstract_excerpt":"3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11613","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/2404.11613/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":"2404.11613","created_at":"2026-07-05T08:09:10.996473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11613v1","created_at":"2026-07-05T08:09:10.996473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11613","created_at":"2026-07-05T08:09:10.996473+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ62PGAWZHT6","created_at":"2026-07-05T08:09:10.996473+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ62PGAWZHT6IM2X","created_at":"2026-07-05T08:09:10.996473+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ62PGAW","created_at":"2026-07-05T08:09:10.996473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27584","citing_title":"CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidance","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29303","citing_title":"Occlusion-Robust Multi-Object Decoupling for Physics-Based Robotic Interaction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29303","citing_title":"Occlusion-Robust Multi-Object Decoupling for Physics-Based Robotic Interaction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09176","citing_title":"LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15843","citing_title":"WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19974","citing_title":"SphericalDreamer: Generating Navigable Immersive 3D Worlds with Panorama Fusion","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00498","citing_title":"GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04331","citing_title":"GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN","json":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN.json","graph_json":"https://pith.science/api/pith-number/WQ62PGAWZHT6IM2XSJ4NLPA2MN/graph.json","events_json":"https://pith.science/api/pith-number/WQ62PGAWZHT6IM2XSJ4NLPA2MN/events.json","paper":"https://pith.science/paper/WQ62PGAW"},"agent_actions":{"view_html":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN","download_json":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN.json","view_paper":"https://pith.science/paper/WQ62PGAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11613&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ62PGAWZHT6IM2XSJ4NLPA2MN/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ62PGAWZHT6IM2XSJ4NLPA2MN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN/action/storage_attestation","attest_author":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN/action/author_attestation","sign_citation":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN/action/citation_signature","submit_replication":"https://pith.science/pith/WQ62PGAWZHT6IM2XSJ4NLPA2MN/action/replication_record"}},"created_at":"2026-07-05T08:09:10.996473+00:00","updated_at":"2026-07-05T08:09:10.996473+00:00"}