{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JC5YNBAIZ4WG7NXORTAFCQA4DK","short_pith_number":"pith:JC5YNBAI","schema_version":"1.0","canonical_sha256":"48bb868408cf2c6fb6ee8cc051401c1aaf093dd5eba5a15063b157c9e9f2aadd","source":{"kind":"arxiv","id":"2412.17630","version":1},"attestation_state":"computed","paper":{"title":"Detail-Preserving Latent Diffusion for Stable Shadow Removal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Wang, Gang Xu, Jiamin Xu, Renshu Gu, Weiwei Xu, Yuxin Zheng, Zelong Li","submitted_at":"2024-12-23T15:06:46Z","abstract_excerpt":"Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal datasets, current methods are prone to overfitting training data, often leading to reduced performance on unseen cases. To address this, we leverage the rich visual priors of a pre-trained Stable Diffusion (SD) model and propose a two-stage fine-tuning pipeline to adapt the SD model for stable and efficient shadow removal. In the first stage, we fix the VAE and fine-tune the denoiser in latent space, which yields substantia"},"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":"2412.17630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T15:06:46Z","cross_cats_sorted":[],"title_canon_sha256":"490914197b8daa6fa5b68e9f90b8ac0ca11104174be15299a1ba7a8eca8271b0","abstract_canon_sha256":"44be1b64cc38c712e371e3f935876d4499d22c7328d02b096d4f4a1cd411833f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:25.165413Z","signature_b64":"wtxZENCp70yOkPvG7RVrR+s09f026SjmKu7aeDEuFLzp9/W1UTGfIAsi1Jfcj3mX0cJnV2dBR5N2AzpYGY1rDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48bb868408cf2c6fb6ee8cc051401c1aaf093dd5eba5a15063b157c9e9f2aadd","last_reissued_at":"2026-07-05T09:53:25.164997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:25.164997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detail-Preserving Latent Diffusion for Stable Shadow Removal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Wang, Gang Xu, Jiamin Xu, Renshu Gu, Weiwei Xu, Yuxin Zheng, Zelong Li","submitted_at":"2024-12-23T15:06:46Z","abstract_excerpt":"Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal datasets, current methods are prone to overfitting training data, often leading to reduced performance on unseen cases. To address this, we leverage the rich visual priors of a pre-trained Stable Diffusion (SD) model and propose a two-stage fine-tuning pipeline to adapt the SD model for stable and efficient shadow removal. In the first stage, we fix the VAE and fine-tune the denoiser in latent space, which yields substantia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17630","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/2412.17630/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":"2412.17630","created_at":"2026-07-05T09:53:25.165058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17630v1","created_at":"2026-07-05T09:53:25.165058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17630","created_at":"2026-07-05T09:53:25.165058+00:00"},{"alias_kind":"pith_short_12","alias_value":"JC5YNBAIZ4WG","created_at":"2026-07-05T09:53:25.165058+00:00"},{"alias_kind":"pith_short_16","alias_value":"JC5YNBAIZ4WG7NXO","created_at":"2026-07-05T09:53:25.165058+00:00"},{"alias_kind":"pith_short_8","alias_value":"JC5YNBAI","created_at":"2026-07-05T09:53:25.165058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK","json":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK.json","graph_json":"https://pith.science/api/pith-number/JC5YNBAIZ4WG7NXORTAFCQA4DK/graph.json","events_json":"https://pith.science/api/pith-number/JC5YNBAIZ4WG7NXORTAFCQA4DK/events.json","paper":"https://pith.science/paper/JC5YNBAI"},"agent_actions":{"view_html":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK","download_json":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK.json","view_paper":"https://pith.science/paper/JC5YNBAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17630&json=true","fetch_graph":"https://pith.science/api/pith-number/JC5YNBAIZ4WG7NXORTAFCQA4DK/graph.json","fetch_events":"https://pith.science/api/pith-number/JC5YNBAIZ4WG7NXORTAFCQA4DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK/action/storage_attestation","attest_author":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK/action/author_attestation","sign_citation":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK/action/citation_signature","submit_replication":"https://pith.science/pith/JC5YNBAIZ4WG7NXORTAFCQA4DK/action/replication_record"}},"created_at":"2026-07-05T09:53:25.165058+00:00","updated_at":"2026-07-05T09:53:25.165058+00:00"}