{"paper":{"title":"Real-Time Neural Hair Denoising","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Neural spatial and temporal reconstruction recovers accurate hair coverage and tangents from undersampled inputs to enable high-quality real-time shading.","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Chenghao Wu, Kai Yan, Kui Wu, Tao Huang, Yuefan Shen, Zahra Montazeri","submitted_at":"2026-05-17T17:37:57Z","abstract_excerpt":"We propose a lightweight real-time method for reconstructing strand-based hair G-Buffers from severely undersampled rasterized inputs. Our pipeline first applies neural spatial reconstruction and temporal accumulation to recover hair coverage, i.e., fractional hair visibility within a pixel, and tangent. It then uses a tangent-guided reconstruction step to complete the position, which is subsequently used for physically based deferred hair shading. We evaluate our method across a diverse set of hairstyles, including straight, wavy, afro, and ponytail styles, under both static and dynamic scena"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our method achieves higher hair reconstruction quality than existing hair-specific denoising techniques and general industrial neural reconstruction solutions such as DLSS and FSR.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The neural spatial reconstruction and temporal accumulation steps can reliably recover accurate fractional hair visibility and tangent from severely undersampled rasterized inputs across diverse hairstyles and motion.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A neural method reconstructs hair G-Buffers from undersampled inputs via spatial-temporal reconstruction and tangent-guided position completion for deferred shading.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural spatial and temporal reconstruction recovers accurate hair coverage and tangents from undersampled inputs to enable high-quality real-time shading.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d1ca68a65d0b01e4f33ecca10def39b16f90fe20647b36c53867216be614783"},"source":{"id":"2605.17557","kind":"arxiv","version":1},"verdict":{"id":"100024f7-73df-4403-b5a5-cdff0b80c9a9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T22:18:05.706416Z","strongest_claim":"Our method achieves higher hair reconstruction quality than existing hair-specific denoising techniques and general industrial neural reconstruction solutions such as DLSS and FSR.","one_line_summary":"A neural method reconstructs hair G-Buffers from undersampled inputs via spatial-temporal reconstruction and tangent-guided position completion for deferred shading.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The neural spatial reconstruction and temporal accumulation steps can reliably recover accurate fractional hair visibility and tangent from severely undersampled rasterized inputs across diverse hairstyles and motion.","pith_extraction_headline":"Neural spatial and temporal reconstruction recovers accurate hair coverage and tangents from undersampled inputs to enable high-quality real-time shading."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17557/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.579128Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:31:07.003020Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.603648Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.536887Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"56a583b2cb7d905efdab9e9f5b5e8ad131e3d6984190287d945d5b8716671ecc"},"references":{"count":59,"sample":[{"doi":"10.48550/arxiv.2310.04080","year":2023,"title":"2023 , eprint =","work_id":"ae748af2-b0ab-475c-9460-661a6c345060","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1989,"title":"Kajiya, J. T. and Kay, T. L. , title =. SIGGRAPH Comput. Graph. , month =. 1989 , issue_date =","work_id":"c1f9fd6f-5591-4d35-a5e6-f88fbbfdbc58","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Marschner and Henrik Wann Jensen and Mike Cammarano and Steve Worley and Pat Hanrahan , title =","work_id":"1f12b4ba-9bec-41de-8fa4-f5acadda8b3a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"ACM SIGGRAPH 2010 Papers , articleno =","work_id":"44fca676-ad32-4627-af8f-01065696b4b9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"A practical approach for photometric acquisition of hair color , journal =","work_id":"987fd5f2-4f4e-40c6-a59d-14f81d92e32e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":59,"snapshot_sha256":"66c183f8a1cac7fa465b743f88fb63dadf354aad144a246ec66bf79ab51beca3","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"}