---
license: cc-by-4.0
pipeline_tag: image-to-image
tags:
- pytorch
- restoration
---

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/1xExposureCorrection_compact)

This model belongs to a series, together with ExposureCorrection and OverExposureCorrection

# 1xUnderExposureCorrection_compact

Name: 1xUnderExposureCorrection_compact  
License: CC BY 4.0  
Author: Philip Hofmann  
Release Date: 27.01.2024  
Network: [SRVGGNetCompact](https://github.com/XPixelGroup/BasicSR/blob/master/basicsr/archs/srvgg_arch.py)  
Scale: 1  
Purpose: 1x exposure correction of underexposed photos  
Iterations: 134'000  
epoch: 84  
batch_size: 12  
HR_size: 128  
Dataset: exposure_correction  
Number of train images: 3534  
OTF Training: No  
Pretrained_Model_G: 1x-Compact-Pretrain  

Description:  
This model is meant as an experiment to see if compact can be used to train on underexposed images to exposure correct those using the pixel, perceptual, color, color and ldl losses. There is no brightness loss. Still it seems to kinda work.

[3 SlowPic Examples](https://slow.pics/s/Lnh2zcuK) 

---
![sculpture_example_underexposurecorrection](https://github.com/Phhofm/models/assets/14755670/41d724b9-f0f3-43dc-99f2-90a4ecfe3f23)
![mountain_example_underexposurecorrection](https://github.com/Phhofm/models/assets/14755670/5f3b032f-00d2-4eb0-aa5e-3b024719a3ad)
![photo_example_underexposurecorrection](https://github.com/Phhofm/models/assets/14755670/94c8cb07-9a97-4a45-baf1-19162d00f518)