-
[pdf]
[supp]
[bibtex]@InProceedings{Tsai_2025_ICCV, author = {Tsai, Shr-Ruei and Chang, Wei-Cheng and Lee, Jie-Ying and Su, Chih-Hai and Liu, Yu-Lun}, title = {LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6353-6363} }
LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
Abstract
Lens flare significantly degrades image quality, impacting critical computer vision tasks like object detection and autonomous driving. Recent Single Image Flare Removal (SIFR) methods perform poorly when off-frame light sources are incomplete or absent. We propose LightsOut, a diffusion-based outpainting framework tailored to enhance SIFR by reconstructing off-frame light sources. Our method leverages a multitask regression module and LoRA fine-tuned diffusion model to ensure realistic and physically consistent outpainting results. Comprehensive experiments demonstrate LightsOut consistently boosts the performance of existing SIFR methods across challenging scenarios without additional retraining, serving as a universally applicable plug-and-play preprocessing solution.
Related Material