LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914099028295680 |
|---|---|
| author | Tsai, Shr-Ruei Chang, Wei-Cheng Lee, Jie-Ying Su, Chih-Hai Liu, Yu-Lun |
| author_facet | Tsai, Shr-Ruei Chang, Wei-Cheng Lee, Jie-Ying Su, Chih-Hai Liu, Yu-Lun |
| contents | 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. Project page: https://ray-1026.github.io/lightsout/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15868 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal Tsai, Shr-Ruei Chang, Wei-Cheng Lee, Jie-Ying Su, Chih-Hai Liu, Yu-Lun Computer Vision and Pattern Recognition 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. Project page: https://ray-1026.github.io/lightsout/ |
| title | LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.15868 |