This repository is the official MegEngine implementation of the 3rd place solution (Team Feedforward) in 2022 MegCup RAW image denoising.
We propose a FeedBack-based Restormer (FBRestormer) for lightweight denoising, the number of parameters in this model is smaller than 100K!
Notice That, the restormer blocks in our architecture are modified by replacing the depth-wise 3x3 convlution in the GDFN with depth-wise 5x5 convlution which is also dilated with dilation equals 2.
The simple gated fusion module is used for feedback connections.
$ conda create -f ./env.yaml
$ conda activate megcupTBD
$ python test.py --data-path DATA_PATH # The test input data path.
--checkpoint CHEKPOINT # The checkpoint need to be loaded.
[--batch-size BATCH_SIZE] # OPTIONAL: Batch size for the dataloader, DEFAULT: 1
[--num-workers NUM_WORKERS] # OPTIONAL: Number of workers for the dataloader, DEFAULT: 0
[--output PATH] # OPTIONAL: The path to output the final binary file, DEFAULT: '.'Example:
$ cp PATH/DATA .
$ python test.py --data-path ./DATA --checkpoint ./feedback_restormer.mge