LightsOut：基於擴散模型的圖像外繪技術，用於強化鏡頭光斑消除

摘要

鏡頭光暈顯著降低影像品質，影響如物件偵測和自動駕駛等關鍵電腦視覺任務。現有的單一影像光暈移除（SIFR）方法在畫面外光源不完整或缺失時表現不佳。我們提出LightsOut，這是一個基於擴散模型的畫面外補全框架，專門用於重建畫面外光源以增強SIFR。我們的方法結合了多任務回歸模組和LoRA微調的擴散模型，確保生成真實且物理一致的畫面外補全結果。全面實驗表明，LightsOut在各種挑戰性場景下持續提升現有SIFR方法的性能，無需額外重新訓練，作為一個普遍適用的即插即用預處理解決方案。專案頁面：https://ray-1026.github.io/lightsout/

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/

LightsOut：基於擴散模型的圖像外繪技術，用於強化鏡頭光斑消除

LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal

摘要

Support