{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KQAM3OCXE5GUASPIM3MVCOMTWY","short_pith_number":"pith:KQAM3OCX","schema_version":"1.0","canonical_sha256":"5400cdb857274d4049e866d9513993b6361b58b054ab81c6d5fc41362e2d924f","source":{"kind":"arxiv","id":"2109.07161","version":2},"attestation_state":"computed","paper":{"title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aleksei Silvestrov, Anastasia Remizova, Anton Mashikhin, Arsenii Ashukha, Elizaveta Logacheva, Harshith Goka, Kiwoong Park, Naejin Kong, Roman Suvorov, Victor Lempitsky","submitted_at":"2021-09-15T08:54:29Z","abstract_excerpt":"Modern image inpainting systems, despite the significant progress, often struggle with large missing areas, complex geometric structures, and high-resolution images. We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function. To alleviate this issue, we propose a new method called large mask inpainting (LaMa). LaMa is based on i) a new inpainting network architecture that uses fast Fourier convolutions (FFCs), which have the image-wide receptive field; ii) a high receptive field perceptual loss; iii) large trai"},"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":"2109.07161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-15T08:54:29Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"11a05583a9d6898214d758f05047cb19111aff5ddc3ee4bd3cbb1d4855558db2","abstract_canon_sha256":"45188ca95d5b29579f2b5d2e73838e647f5d547b8ab81f0794114038b076ff0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:54.125802Z","signature_b64":"OZY7GhgIKja9AyHg8/fGbNuGXCJAAFh1112nb/06OEUwKhhAPDEWX9ywAg92YGgST2lq1ssbVgDbV+9VH8EfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5400cdb857274d4049e866d9513993b6361b58b054ab81c6d5fc41362e2d924f","last_reissued_at":"2026-07-05T03:30:54.125293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:54.125293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aleksei Silvestrov, Anastasia Remizova, Anton Mashikhin, Arsenii Ashukha, Elizaveta Logacheva, Harshith Goka, Kiwoong Park, Naejin Kong, Roman Suvorov, Victor Lempitsky","submitted_at":"2021-09-15T08:54:29Z","abstract_excerpt":"Modern image inpainting systems, despite the significant progress, often struggle with large missing areas, complex geometric structures, and high-resolution images. We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function. To alleviate this issue, we propose a new method called large mask inpainting (LaMa). LaMa is based on i) a new inpainting network architecture that uses fast Fourier convolutions (FFCs), which have the image-wide receptive field; ii) a high receptive field perceptual loss; iii) large trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07161","kind":"arxiv","version":2},"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/2109.07161/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":"2109.07161","created_at":"2026-07-05T03:30:54.125358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.07161v2","created_at":"2026-07-05T03:30:54.125358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07161","created_at":"2026-07-05T03:30:54.125358+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQAM3OCXE5GU","created_at":"2026-07-05T03:30:54.125358+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQAM3OCXE5GUASPI","created_at":"2026-07-05T03:30:54.125358+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQAM3OCX","created_at":"2026-07-05T03:30:54.125358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19195","citing_title":"Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17520","citing_title":"GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07079","citing_title":"AsyncPatch Diffusion: spatially-flexible image generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30239","citing_title":"CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30987","citing_title":"Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20290","citing_title":"PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21834","citing_title":"PrefPaint: Enhancing Medical Image Inpainting through Expert Human Feedback","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2302.11550","citing_title":"Scaling Robot Learning with Semantically Imagined Experience","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16515","citing_title":"Generative deep learning improves reconstruction of global historical climate records","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00799","citing_title":"Multimodal Language Models Cannot Spot Spatial Inconsistencies","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25459","citing_title":"GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY","json":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY.json","graph_json":"https://pith.science/api/pith-number/KQAM3OCXE5GUASPIM3MVCOMTWY/graph.json","events_json":"https://pith.science/api/pith-number/KQAM3OCXE5GUASPIM3MVCOMTWY/events.json","paper":"https://pith.science/paper/KQAM3OCX"},"agent_actions":{"view_html":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY","download_json":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY.json","view_paper":"https://pith.science/paper/KQAM3OCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.07161&json=true","fetch_graph":"https://pith.science/api/pith-number/KQAM3OCXE5GUASPIM3MVCOMTWY/graph.json","fetch_events":"https://pith.science/api/pith-number/KQAM3OCXE5GUASPIM3MVCOMTWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY/action/storage_attestation","attest_author":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY/action/author_attestation","sign_citation":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY/action/citation_signature","submit_replication":"https://pith.science/pith/KQAM3OCXE5GUASPIM3MVCOMTWY/action/replication_record"}},"created_at":"2026-07-05T03:30:54.125358+00:00","updated_at":"2026-07-05T03:30:54.125358+00:00"}