English

Lasagna: Layered Score Distillation for Disentangled Object Relighting

Computer Vision and Pattern Recognition 2023-12-05 v1

Abstract

Professional artists, photographers, and other visual content creators use object relighting to establish their photo's desired effect. Unfortunately, manual tools that allow relighting have a steep learning curve and are difficult to master. Although generative editing methods now enable some forms of image editing, relighting is still beyond today's capabilities; existing methods struggle to keep other aspects of the image -- colors, shapes, and textures -- consistent after the edit. We propose Lasagna, a method that enables intuitive text-guided relighting control. Lasagna learns a lighting prior by using score distillation sampling to distill the prior of a diffusion model, which has been finetuned on synthetic relighting data. To train Lasagna, we curate a new synthetic dataset ReLiT, which contains 3D object assets re-lit from multiple light source locations. Despite training on synthetic images, quantitative results show that Lasagna relights real-world images while preserving other aspects of the input image, outperforming state-of-the-art text-guided image editing methods. Lasagna enables realistic and controlled results on natural images and digital art pieces and is preferred by humans over other methods in over 91% of cases. Finally, we demonstrate the versatility of our learning objective by extending it to allow colorization, another form of image editing.

Keywords

Cite

@article{arxiv.2312.00833,
  title  = {Lasagna: Layered Score Distillation for Disentangled Object Relighting},
  author = {Dina Bashkirova and Arijit Ray and Rupayan Mallick and Sarah Adel Bargal and Jianming Zhang and Ranjay Krishna and Kate Saenko},
  journal= {arXiv preprint arXiv:2312.00833},
  year   = {2023}
}
R2 v1 2026-06-28T13:38:44.915Z