{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7PF76WUYAEERRQYOUIXRQ2DSBU","short_pith_number":"pith:7PF76WUY","schema_version":"1.0","canonical_sha256":"fbcbff5a98010918c30ea22f1868720d1f9a7e2cb65dfdc85aea0246cc0f1c3e","source":{"kind":"arxiv","id":"2304.06790","version":1},"attestation_state":"computed","paper":{"title":"Inpaint Anything: Segment Anything Meets Image Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinming Liu, Runseng Feng, Ruoyu Feng, Tao Yu, Wenjun Zeng, Xin Jin, Zhibo Chen","submitted_at":"2023-04-13T19:23:52Z","abstract_excerpt":"Modern image inpainting systems, despite the significant progress, often struggle with mask selection and holes filling. Based on Segment-Anything Model (SAM), we make the first attempt to the mask-free image inpainting and propose a new paradigm of ``clicking and filling'', which is named as Inpaint Anything (IA). The core idea behind IA is to combine the strengths of different models in order to build a very powerful and user-friendly pipeline for solving inpainting-related problems. IA supports three main features: (i) Remove Anything: users could click on an object and IA will remove it an"},"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":"2304.06790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T19:23:52Z","cross_cats_sorted":[],"title_canon_sha256":"6789923ece4ff265dc86106532fc59d0968226c190302dee115aeb92dd6f0153","abstract_canon_sha256":"36f40d5069622ae0345b92df4fcdea223a1d5d3f139a4888d762d0ea92483b0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:01.911519Z","signature_b64":"cwujTGiSBvqlFjcojb/wtDXnmjial2quy4R3r5BIUKwsqKVn5T5M8U0nGCpKxLUXbzHVMxD8qwzobdHEKTYZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbcbff5a98010918c30ea22f1868720d1f9a7e2cb65dfdc85aea0246cc0f1c3e","last_reissued_at":"2026-07-05T06:01:01.910875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:01.910875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inpaint Anything: Segment Anything Meets Image Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinming Liu, Runseng Feng, Ruoyu Feng, Tao Yu, Wenjun Zeng, Xin Jin, Zhibo Chen","submitted_at":"2023-04-13T19:23:52Z","abstract_excerpt":"Modern image inpainting systems, despite the significant progress, often struggle with mask selection and holes filling. Based on Segment-Anything Model (SAM), we make the first attempt to the mask-free image inpainting and propose a new paradigm of ``clicking and filling'', which is named as Inpaint Anything (IA). The core idea behind IA is to combine the strengths of different models in order to build a very powerful and user-friendly pipeline for solving inpainting-related problems. IA supports three main features: (i) Remove Anything: users could click on an object and IA will remove it an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06790","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/2304.06790/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":"2304.06790","created_at":"2026-07-05T06:01:01.910968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06790v1","created_at":"2026-07-05T06:01:01.910968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06790","created_at":"2026-07-05T06:01:01.910968+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PF76WUYAEER","created_at":"2026-07-05T06:01:01.910968+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PF76WUYAEERRQYO","created_at":"2026-07-05T06:01:01.910968+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PF76WUY","created_at":"2026-07-05T06:01:01.910968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19676","citing_title":"TeleMorpher: Toward Robust Simultaneous Motion-Location Editing","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17520","citing_title":"GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06228","citing_title":"SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00078","citing_title":"Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04960","citing_title":"On Efficient Variants of Segment Anything Model: A Survey","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18361","citing_title":"COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14289","citing_title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":53,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06171","citing_title":"Automated Annotation of Shearographic Measurements Enabling Weakly Supervised Defect Detection","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14461","citing_title":"ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11818","citing_title":"RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12443","citing_title":"DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07940","citing_title":"Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU","json":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU.json","graph_json":"https://pith.science/api/pith-number/7PF76WUYAEERRQYOUIXRQ2DSBU/graph.json","events_json":"https://pith.science/api/pith-number/7PF76WUYAEERRQYOUIXRQ2DSBU/events.json","paper":"https://pith.science/paper/7PF76WUY"},"agent_actions":{"view_html":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU","download_json":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU.json","view_paper":"https://pith.science/paper/7PF76WUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06790&json=true","fetch_graph":"https://pith.science/api/pith-number/7PF76WUYAEERRQYOUIXRQ2DSBU/graph.json","fetch_events":"https://pith.science/api/pith-number/7PF76WUYAEERRQYOUIXRQ2DSBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU/action/storage_attestation","attest_author":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU/action/author_attestation","sign_citation":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU/action/citation_signature","submit_replication":"https://pith.science/pith/7PF76WUYAEERRQYOUIXRQ2DSBU/action/replication_record"}},"created_at":"2026-07-05T06:01:01.910968+00:00","updated_at":"2026-07-05T06:01:01.910968+00:00"}