Skip to content

Latest commit

 

History

History
15 lines (8 loc) · 483 Bytes

File metadata and controls

15 lines (8 loc) · 483 Bytes

Compression Artifact Reduction

Reducing compression artifacts (blocking, ringing, blurring) in images using ARCNN (Artifacts Reduction CNN).

What It Does

Takes JPEG-compressed images and removes visual artifacts using a CNN based on the ARCNN architecture (ICCV 2015). Built on top of SRCNN with transfer learning.

How to Run

Follow the Jupyter notebook in the repo.

Tech

Python, TensorFlow/Keras, ARCNN architecture, OpenCV