{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/53e314e8-fa93-47f6-aef5-1d8fb480ed18","identifier":"53e314e8-fa93-47f6-aef5-1d8fb480ed18","url":"https://forgecascade.org/public/capsules/53e314e8-fa93-47f6-aef5-1d8fb480ed18","name":"PIXLRelight: Controllable Relighting via Intrinsic Conditioning","text":"# PIXLRelight: Controllable Relighting via Intrinsic Conditioning\n\n**Authors:** Miguel Farinha, Ronald Clark\n**arXiv:** https://arxiv.org/abs/2605.18735v1\n**Published:** 2026-05-18T17:55:03Z\n\n## Abstract\nWe present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or environment maps), accumulate errors when chaining inverse and forward rendering, or require costly per-image optimization. Our key idea is to bridge physically based rendering (PBR) and learned image synthesis through a shared intrinsic conditioning that can be obtained from either real photographs or PBR renders. At training time, paired multi-illumination photographs are decomposed into albedo, diffuse shading, and non-diffuse residuals, which condition the model. At inference time, the same conditioning is computed from a path-traced render of a coarse 3D reconstruction of the input under user-specified PBR lights. A transformer-based neural renderer then applies the target illumination to the source photograph, preserving fine image detail through a per-pixel affine modulation. PIXLRelight enables arbitrary PBR-style lighting control, achieves state-of-the-art relighting quality, and runs in under a tenth of a second per image. Code and models are available at https://mlfarinha.github.io/pixl-relight/.","keywords":["cs.CV","cs.GR","cs.LG"],"about":[{"@type":"Thing","name":"Patchwork"},{"@type":"Thing","name":"Confucius"},{"@type":"Thing","name":"VERMIN"},{"@type":"Thing","name":"cmd"},{"@type":"Thing","name":"Sagerunex"},{"@type":"Thing","name":"Code Signing"},{"@type":"Thing","name":"Code Repositories"},{"@type":"Thing","name":"Office Template Macros"}],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-19T06:00:07.282000Z","dateModified":"2026-05-19T06:00:07.282000Z","isBasedOn":"https://arxiv.org/abs/2605.18735v1","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":65},{"@type":"PropertyValue","name":"verification_status","value":"source_linked"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"}]}