{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQ3BQ32Y7GR2E7MP4BLTAQIWZO","short_pith_number":"pith:ZQ3BQ32Y","schema_version":"1.0","canonical_sha256":"cc36186f58f9a3a27d8fe057304116cbbbaa712360376f46b381830ecfdb81ae","source":{"kind":"arxiv","id":"2501.07397","version":3},"attestation_state":"computed","paper":{"title":"OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ban, Hao Sun, Kongming Liang, Lanxiang Zhou, Runpu Wei, Shuo Zhang, Tianwei Cao, Xueyi Wang, Zhanyu Ma, Zhongjiang He, Zijin Yin","submitted_at":"2025-01-13T15:12:40Z","abstract_excerpt":"Inpainting algorithms have achieved remarkable progress in removing objects from images, yet still face two challenges: 1) struggle to handle the object's visual effects such as shadow and reflection; 2) easily generate shape-like artifacts and unintended content. In this paper, we propose Video4Removal, a large-scale dataset comprising over 100,000 high-quality samples with realistic object shadows and reflections. By constructing object-background pairs from video frames with off-the-shelf vision models, the labor costs of data acquisition can be significantly reduced. To avoid generating sh"},"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":"2501.07397","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T15:12:40Z","cross_cats_sorted":[],"title_canon_sha256":"951e14a5a5db4d16b99e9e1fe94535eed690d2c4abfb7378103170abfa72e820","abstract_canon_sha256":"46bf75a7af0e41e55910fa6e8c15dbaae1dc287bb62adc89ac9872179a89659a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:32.362017Z","signature_b64":"rgiZPTN95p7Cy5ZV49MwJR/qnJOS9poxUJRRL0zdEt3+2uY7xOSn7SgXX+ALn40dHG+CZ6nyR6o4kCevMPrOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc36186f58f9a3a27d8fe057304116cbbbaa712360376f46b381830ecfdb81ae","last_reissued_at":"2026-07-05T10:28:32.361468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:32.361468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ban, Hao Sun, Kongming Liang, Lanxiang Zhou, Runpu Wei, Shuo Zhang, Tianwei Cao, Xueyi Wang, Zhanyu Ma, Zhongjiang He, Zijin Yin","submitted_at":"2025-01-13T15:12:40Z","abstract_excerpt":"Inpainting algorithms have achieved remarkable progress in removing objects from images, yet still face two challenges: 1) struggle to handle the object's visual effects such as shadow and reflection; 2) easily generate shape-like artifacts and unintended content. In this paper, we propose Video4Removal, a large-scale dataset comprising over 100,000 high-quality samples with realistic object shadows and reflections. By constructing object-background pairs from video frames with off-the-shelf vision models, the labor costs of data acquisition can be significantly reduced. To avoid generating sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07397","kind":"arxiv","version":3},"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/2501.07397/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":"2501.07397","created_at":"2026-07-05T10:28:32.361527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07397v3","created_at":"2026-07-05T10:28:32.361527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07397","created_at":"2026-07-05T10:28:32.361527+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ3BQ32Y7GR2","created_at":"2026-07-05T10:28:32.361527+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ3BQ32Y7GR2E7MP","created_at":"2026-07-05T10:28:32.361527+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ3BQ32Y","created_at":"2026-07-05T10:28:32.361527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25548","citing_title":"Concept Removal for Frontier Image Generative Models","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04545","citing_title":"Impostor: An Agent-Curated Benchmark for Realistic AIGC Manipulation Localization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28094","citing_title":"OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30045","citing_title":"GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15507","citing_title":"A Unified and Controllable Framework for Layered Image Generation with Visual Effects","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14534","citing_title":"PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14399","citing_title":"SceneForge: Structured World Supervision from 3D Interventions","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09003","citing_title":"FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09003","citing_title":"FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06658","citing_title":"Relit-LiVE: Relight Video by Jointly Learning Environment Video","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19624","citing_title":"GRAFT: Geometric Refinement and Fitting Transformer for Human Scene Reconstruction","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO","json":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO.json","graph_json":"https://pith.science/api/pith-number/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/graph.json","events_json":"https://pith.science/api/pith-number/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/events.json","paper":"https://pith.science/paper/ZQ3BQ32Y"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO","download_json":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO.json","view_paper":"https://pith.science/paper/ZQ3BQ32Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07397&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ3BQ32Y7GR2E7MP4BLTAQIWZO/action/replication_record"}},"created_at":"2026-07-05T10:28:32.361527+00:00","updated_at":"2026-07-05T10:28:32.361527+00:00"}