{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UDINQD7R6AVNHRGAXERPBA2Y42","short_pith_number":"pith:UDINQD7R","schema_version":"1.0","canonical_sha256":"a0d0d80ff1f02ad3c4c0b922f08358e6a0edb70527314485eb544cb396ae2388","source":{"kind":"arxiv","id":"2312.17334","version":1},"attestation_state":"computed","paper":{"title":"Improving Image Restoration through Removing Degradations in Textual Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsheng Jiang, Dongwei Ren, Jingbo Lin, Wangmeng Zuo, Yuxiang Wei, Zhilu Zhang","submitted_at":"2023-12-28T19:18:17Z","abstract_excerpt":"In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restoration is much easier on text modality than image one. For example, it can be easily conducted by removing degradation-related words while keeping the content-aware words. Hence, we combine the advantages of images in detail description and ones of text in degradation removal to perform restoration. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing th"},"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":"2312.17334","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T19:18:17Z","cross_cats_sorted":[],"title_canon_sha256":"4145d959f8e87ce87b956199b044f195c56729ede33348066932dc24ebe98baa","abstract_canon_sha256":"7adb17cc900e3721650c2c5875d5e42377832d0eb954a6af135a66ba5fff46e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:49.473770Z","signature_b64":"4xOioYcIT3MXcqv9ZPuEqoDQoVk2sZlUdi3BD3XQ3w7qM16Vq2k76Lx5zchlG3av+U7KU1/fBfYngVMvpRi3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d0d80ff1f02ad3c4c0b922f08358e6a0edb70527314485eb544cb396ae2388","last_reissued_at":"2026-07-05T07:28:49.473229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:49.473229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Image Restoration through Removing Degradations in Textual Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsheng Jiang, Dongwei Ren, Jingbo Lin, Wangmeng Zuo, Yuxiang Wei, Zhilu Zhang","submitted_at":"2023-12-28T19:18:17Z","abstract_excerpt":"In this paper, we introduce a new perspective for improving image restoration by removing degradation in the textual representations of a given degraded image. Intuitively, restoration is much easier on text modality than image one. For example, it can be easily conducted by removing degradation-related words while keeping the content-aware words. Hence, we combine the advantages of images in detail description and ones of text in degradation removal to perform restoration. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17334","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/2312.17334/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":"2312.17334","created_at":"2026-07-05T07:28:49.473288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17334v1","created_at":"2026-07-05T07:28:49.473288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17334","created_at":"2026-07-05T07:28:49.473288+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDINQD7R6AVN","created_at":"2026-07-05T07:28:49.473288+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDINQD7R6AVNHRGA","created_at":"2026-07-05T07:28:49.473288+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDINQD7R","created_at":"2026-07-05T07:28:49.473288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14851","citing_title":"Grounding Degradations in Natural Language for All-In-One Video Restoration","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42","json":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42.json","graph_json":"https://pith.science/api/pith-number/UDINQD7R6AVNHRGAXERPBA2Y42/graph.json","events_json":"https://pith.science/api/pith-number/UDINQD7R6AVNHRGAXERPBA2Y42/events.json","paper":"https://pith.science/paper/UDINQD7R"},"agent_actions":{"view_html":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42","download_json":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42.json","view_paper":"https://pith.science/paper/UDINQD7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17334&json=true","fetch_graph":"https://pith.science/api/pith-number/UDINQD7R6AVNHRGAXERPBA2Y42/graph.json","fetch_events":"https://pith.science/api/pith-number/UDINQD7R6AVNHRGAXERPBA2Y42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42/action/storage_attestation","attest_author":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42/action/author_attestation","sign_citation":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42/action/citation_signature","submit_replication":"https://pith.science/pith/UDINQD7R6AVNHRGAXERPBA2Y42/action/replication_record"}},"created_at":"2026-07-05T07:28:49.473288+00:00","updated_at":"2026-07-05T07:28:49.473288+00:00"}