{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XVQ4RTNU4SB2HB4EIG7KY3R7BL","short_pith_number":"pith:XVQ4RTNU","schema_version":"1.0","canonical_sha256":"bd61c8cdb4e483a3878441beac6e3f0ac29fae65f8d8838fc16f61dd77f021e1","source":{"kind":"arxiv","id":"2107.07235","version":1},"attestation_state":"computed","paper":{"title":"Deep Automatic Natural Image Matting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jing Zhang, Jizhizi Li","submitted_at":"2021-07-15T10:29:01Z","abstract_excerpt":"Automatic image matting (AIM) refers to estimating the soft foreground from an arbitrary natural image without any auxiliary input like trimap, which is useful for image editing. Prior methods try to learn semantic features to aid the matting process while being limited to images with salient opaque foregrounds such as humans and animals. In this paper, we investigate the difficulties when extending them to natural images with salient transparent/meticulous foregrounds or non-salient foregrounds. To address the problem, a novel end-to-end matting network is proposed, which can predict a genera"},"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":"2107.07235","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-15T10:29:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5a7cfce1ce8796b5496a2120bb94754dbdfd232dda8fd056ab2bbcd93532113","abstract_canon_sha256":"24a1f08f9df6bfef27ff4cec7ede77f4ea8488e6b9a6ccecddd8469958f42b28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:12.156015Z","signature_b64":"q0DHSkBpuwDYpqVKATHdjlL3bPveff/xCT7xlA34xhtI9Mg925By+zoldcfQn8gE5Qh4GxcNa0DS/LT8SWZ0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd61c8cdb4e483a3878441beac6e3f0ac29fae65f8d8838fc16f61dd77f021e1","last_reissued_at":"2026-07-05T02:58:12.155604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:12.155604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Automatic Natural Image Matting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jing Zhang, Jizhizi Li","submitted_at":"2021-07-15T10:29:01Z","abstract_excerpt":"Automatic image matting (AIM) refers to estimating the soft foreground from an arbitrary natural image without any auxiliary input like trimap, which is useful for image editing. Prior methods try to learn semantic features to aid the matting process while being limited to images with salient opaque foregrounds such as humans and animals. In this paper, we investigate the difficulties when extending them to natural images with salient transparent/meticulous foregrounds or non-salient foregrounds. To address the problem, a novel end-to-end matting network is proposed, which can predict a genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07235","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/2107.07235/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":"2107.07235","created_at":"2026-07-05T02:58:12.155678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07235v1","created_at":"2026-07-05T02:58:12.155678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07235","created_at":"2026-07-05T02:58:12.155678+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVQ4RTNU4SB2","created_at":"2026-07-05T02:58:12.155678+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVQ4RTNU4SB2HB4E","created_at":"2026-07-05T02:58:12.155678+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVQ4RTNU","created_at":"2026-07-05T02:58:12.155678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27339","citing_title":"SAM2Matting: Generalized Image and Video Matting","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18328","citing_title":"CineMatte: Background Matting for Virtual Production and Beyond","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07429","citing_title":"Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07429","citing_title":"Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL","json":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL.json","graph_json":"https://pith.science/api/pith-number/XVQ4RTNU4SB2HB4EIG7KY3R7BL/graph.json","events_json":"https://pith.science/api/pith-number/XVQ4RTNU4SB2HB4EIG7KY3R7BL/events.json","paper":"https://pith.science/paper/XVQ4RTNU"},"agent_actions":{"view_html":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL","download_json":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL.json","view_paper":"https://pith.science/paper/XVQ4RTNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07235&json=true","fetch_graph":"https://pith.science/api/pith-number/XVQ4RTNU4SB2HB4EIG7KY3R7BL/graph.json","fetch_events":"https://pith.science/api/pith-number/XVQ4RTNU4SB2HB4EIG7KY3R7BL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL/action/storage_attestation","attest_author":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL/action/author_attestation","sign_citation":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL/action/citation_signature","submit_replication":"https://pith.science/pith/XVQ4RTNU4SB2HB4EIG7KY3R7BL/action/replication_record"}},"created_at":"2026-07-05T02:58:12.155678+00:00","updated_at":"2026-07-05T02:58:12.155678+00:00"}