用扩散模型补全镜头光晕缺失部分，提升图像修复效果
LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal
- 用扩散模型和回归模块重建画面外的光源
- 在复杂场景下显著提升现有去光晕方法的性能
- 无需重新训练，可直接接入现有系统
镜头光晕严重降低图像质量，影响目标检测与自动驾驶等关键任务。现有单图像去光晕（SIFR）方法在画面外光源不完整或缺失时表现不佳。我们提出LightsOut，一种基于扩散模型的外延生成框架，通过多任务回归模块与LoRA微调的扩散模型，实现真实且物理一致的光源外推。大量实验表明，LightsOut能持续提升现有SIFR方法在挑战性场景下的表现，无需额外训练，可作为通用的即插即用预处理方案。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。