README.md

Image Lens Flare Removal Using Adversarial Curve Learning

This repository provides the official implementation for the following two papers:

Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery (ICCV 2023)

Image Lens Flare Removal Using Adversarial Curve Learning arxiv 2024

Dataset

Training data

Wu el al. training images are provided in How to Train Neural Networks for Flare Removal (Wu et al. ICCV 2021)

Flare7K training images are provided in Flare7K: A Phenomenological Nighttime Flare Removal Dataset (Dai et al. NeurIPS 2022).

Please follow their instructions to access the data.

Test data

The consumer electronics dataset can be downloaded in Google Cloud or Baidu Netdisk (password：ptb3).

Pre-trained Model

The inference code based on Uformer can be downloaded in Google Cloud or Baidu Netdisk (password: vmxl).

Code

The backbone of our code is from Wu et al. How to Train Neural Networks for Flare Removal. We imporve the synthesis pipeline and light source recovery method to obtain better performance on flare removal.

Train

python train.py	  --flarec_dir=path/to/captured/flare   --flares_dir=path/to/simulated/flare    --scene_dir=path/to/scene/image

Test

python  remove_flare.py   --input_dir=path/to/test/image/dir   --out_dir=path/to/output/dir --model=Uformer    --batch_size=2    --ckpt=path/to/pretrained/model