https://github.com/tallamjr/clic

Challenge for Learning Image Compression, 2021
https://github.com/tallamjr/clic

compression cvpr image-compression lossy-compression video-compression video-processing

Last synced: about 1 month ago
JSON representation

Challenge for Learning Image Compression, 2021

• Host: GitHub
• URL: https://github.com/tallamjr/clic
• Owner: tallamjr
• License: mit
• Created: 2021-01-13T22:16:04.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2021-02-14T13:39:01.000Z (about 4 years ago)
• Last Synced: 2025-02-10T02:38:11.511Z (3 months ago)
• Topics: compression, cvpr, image-compression, lossy-compression, video-compression, video-processing
• Language: Python
• Homepage: http://compression.cc/
• Size: 207 KB
• Stars: 2
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
### CVPR Workshop: Challenge for Learning Image Compression

[2020 Papers](https://openaccess.thecvf.com/CVPR2020_workshops/CVPR2020_w7)

#### Evaluation Metrics

> The `evaluate()` in `metrics.py` function expects two dictionaries mapping filenames fo filepaths (the target PNGs and PNGs produced by the decoder).

> I attached the code that's used to evaluate submissions. The function `evaluate()` in `metrics.py` receives two dictionaries containing paths to the target PNGs and decoded PNGs. In the video challenge, these are the PNGs representing Y, U, and V channels. One thing to note is that the MS-SSIM is weighted by the number of pixels, so Y is weighted more strongly than U or V.

> - Lucas