{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7K2JO5BOIKH2XGLAXQHQCYZOML","short_pith_number":"pith:7K2JO5BO","schema_version":"1.0","canonical_sha256":"fab497742e428fab9960bc0f01632e62d46d84eaf39be8ecf5cad4d47e5a2c50","source":{"kind":"arxiv","id":"2505.24873","version":1},"attestation_state":"computed","paper":{"title":"MiniMax-Remover: Taming Bad Noise Helps Video Object Removal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bojia Zi, Jianan Wang, Kam-Fai Wong, Rong Xiao, Shihao Zhao, Weixuan Peng, Xianbiao Qi","submitted_at":"2025-05-30T17:59:45Z","abstract_excerpt":"Recent advances in video diffusion models have driven rapid progress in video editing techniques. However, video object removal, a critical subtask of video editing, remains challenging due to issues such as hallucinated objects and visual artifacts. Furthermore, existing methods often rely on computationally expensive sampling procedures and classifier-free guidance (CFG), resulting in slow inference. To address these limitations, we propose MiniMax-Remover, a novel two-stage video object removal approach. Motivated by the observation that text condition is not best suited for this task, we s"},"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":"2505.24873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T17:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"6b57b6b01fd3633940dbf5fd76313924b817f9c1eeb5f058732bed39d983d732","abstract_canon_sha256":"690e203cd9dad695d11f96292e7289bfc1f9b580bd9a4c087a12e7eaa1230455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:58.114413Z","signature_b64":"8h2HvkQMUH9y0/K3AQPde3zhDfMBpIwZX+ynf4JgXCf/ilSWePBNPzesIBa0FiDp3x1ccgQtq4CCVPosGndMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fab497742e428fab9960bc0f01632e62d46d84eaf39be8ecf5cad4d47e5a2c50","last_reissued_at":"2026-07-05T11:12:58.113854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:58.113854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MiniMax-Remover: Taming Bad Noise Helps Video Object Removal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bojia Zi, Jianan Wang, Kam-Fai Wong, Rong Xiao, Shihao Zhao, Weixuan Peng, Xianbiao Qi","submitted_at":"2025-05-30T17:59:45Z","abstract_excerpt":"Recent advances in video diffusion models have driven rapid progress in video editing techniques. However, video object removal, a critical subtask of video editing, remains challenging due to issues such as hallucinated objects and visual artifacts. Furthermore, existing methods often rely on computationally expensive sampling procedures and classifier-free guidance (CFG), resulting in slow inference. To address these limitations, we propose MiniMax-Remover, a novel two-stage video object removal approach. Motivated by the observation that text condition is not best suited for this task, we s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24873","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/2505.24873/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":"2505.24873","created_at":"2026-07-05T11:12:58.113921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24873v1","created_at":"2026-07-05T11:12:58.113921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24873","created_at":"2026-07-05T11:12:58.113921+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K2JO5BOIKH2","created_at":"2026-07-05T11:12:58.113921+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K2JO5BOIKH2XGLA","created_at":"2026-07-05T11:12:58.113921+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K2JO5BO","created_at":"2026-07-05T11:12:58.113921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":59,"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":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23192","citing_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23891","citing_title":"Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15533","citing_title":"Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14534","citing_title":"PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21901","citing_title":"CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML","json":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML.json","graph_json":"https://pith.science/api/pith-number/7K2JO5BOIKH2XGLAXQHQCYZOML/graph.json","events_json":"https://pith.science/api/pith-number/7K2JO5BOIKH2XGLAXQHQCYZOML/events.json","paper":"https://pith.science/paper/7K2JO5BO"},"agent_actions":{"view_html":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML","download_json":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML.json","view_paper":"https://pith.science/paper/7K2JO5BO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24873&json=true","fetch_graph":"https://pith.science/api/pith-number/7K2JO5BOIKH2XGLAXQHQCYZOML/graph.json","fetch_events":"https://pith.science/api/pith-number/7K2JO5BOIKH2XGLAXQHQCYZOML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML/action/storage_attestation","attest_author":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML/action/author_attestation","sign_citation":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML/action/citation_signature","submit_replication":"https://pith.science/pith/7K2JO5BOIKH2XGLAXQHQCYZOML/action/replication_record"}},"created_at":"2026-07-05T11:12:58.113921+00:00","updated_at":"2026-07-05T11:12:58.113921+00:00"}