6 papers · 1 filter
N-O Cool-chic: reconcile fast encoding with lightweight decoding for neural image compression
Théophile Blard, Théo Ladune, Pierrick Philippe +2
Overfitted image codecs achieve strong compression performance and low decoder complexity by learning a lightweight decoder for each image. Such codecs include Cool-chic, which pre…
Spatial Competition for Low-Complexity Learned Image Compression
Théophile Blard, Pierrick Philippe, Théo Ladune +2
Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a…
Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression
Théo Ladune, Pierrick Philippe, Pierre Jaffuer +4
Overfitted codecs compress an image by learning a decoder tailored to the content during the encoding. As such, they trade increased encoding complexity for strong compression perf…
Upsampling Improvement for Overfitted Neural Coding
Pierrick Philippe, Théo Ladune, Gordon Clare +3
Neural image compression, based on auto-encoders and overfitted representations, relies on a latent representation of the coded signal. This representation needs to be compact and…
Cool-chic video: Learned video coding with 800 parameters
Thomas Leguay, Théo Ladune, Pierrick Philippe +1
We propose a lightweight learned video codec with 900 multiplications per decoded pixel and 800 parameters overall. To the best of our knowledge, this is one of the neural video co…
Cool-Chic: Perceptually Tuned Low Complexity Overfitted Image Coder
Théo Ladune, Pierrick Philippe, Gordon Clare +2
This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can le…