Théo Ladune

Logo

PhD in signal processing from University of Rennes, France.

My research interests include image/video coding using learning-based methods.

View My GitHub Profile

Add me on LinkedIn

Google scholar

Checkout our open-source lightweight learned codec Cool-chic 😎

Short Bio

I defended my PhD on “Design of Learned Video Coding Schemes” in October 2021. My current work focuses on Cool-chic, a lightweight neural image & video codec based on overfitting.

Updates

Publications

My current work revolves around the design of Cool-chic, an open-source lightweight neural image & video codec based on overfiting. Some relevevant papers about Cool-chic are:

Cool-chic video: Learned video coding with 800 parameters

DCC24

T. Leguay,, T. Ladune, P. Philippe, O. Déforges IEEE DCC 2024

Paper / Code

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 codecs with the lowest decoding complexity. It is built upon the overfitted image codec Cool-chic and supplements it with an inter coding module to leverage the video’s temporal redundancies. The proposed model is able to compress videos using both low-delay and random access configurations and achieves rate-distortion close to AVC while out-performing other overfitted codecs such as FFNeRV. The system is made open-source.

Low-complexity Overfitted Neural Image Codec

MMSP23

T. Leguay,, T. Ladune, P. Philippe, C. Clare, F. Henry IEEE MMSP 2023

Paper / Code

We propose a neural image codec at reduced complexity which overfits the decoder parameters to each input image. While autoencoders perform up to a million multiplications per decoded pixel, the proposed approach only requires 2300 multiplications per pixel. Albeit low-complexity, the method rivals autoencoder performance and surpasses HEVC performance under various coding conditions. Additional lightweight modules and an improved training process provide a 14% rate reduction with respect to previous overfitted codecs, while offering a similar complexity. This work is made open-source.

COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec

ICCV23

T. Ladune, P. Philippe, F. Henry, C. Clare, T. Leguay, ICCV 2023

Paper / Code

We introduce COOL-CHIC, a Coordinate-based Low Complexity Hierarchical Image Codec. It is a learned alternative to autoencoders with 629 parameters and 680 multiplications per decoded pixel. COOL-CHIC offers compression performance close to modern conventional MPEG codecs such as HEVC and is competitive with popular autoencoder-based systems. This method is inspired by Coordinate-based Neural Representations, where an image is represented as a learned function which maps pixel coordinates to RGB values. The parameters of the mapping function are then sent using entropy coding. At the receiver side, the compressed image is obtained by evaluating the mapping function for all pixel coordinates. COOL-CHIC implementation is made open-source.

Other papers relevant for Cool-chic

My first few papers were centered around the design of AIVC, an open-source autoencoder-based video codec. Two important papers stand out among them:

Conditional Coding for Flexible Learned Video Compression

ICLR21

T. Ladune, P. Philippe, W. Hamidouche, L. Zhang, O. Déforges, ICLR 2021, Neural Compression Workshop

Paper / Video presentation / Slides

This paper introduces a novel framework for end-to-end learned video coding. Image compression is generalized through conditional coding to exploit information from reference frames, allowing to process intra and inter frames with the same coder. The system is trained through the minimization of a rate-distortion cost, with no pre-training or proxy loss. Its flexibility is assessed under three coding configurations (All Intra, Low-delay P and Random Access), where it is shown to achieve performance competitive with the state-of-the-art video codec HEVC.

Optical Flow and Mode Selection for Learning-based Video Coding

MOFNet

T. Ladune, P. Philippe, W. Hamidouche, L. Zhang, O. Déforges, IEEE MMSP 2020

Paper / Video presentation / Slides

This work received the best paper award at the MMSP 2020 conference 🥇.

This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used to perform a prediction of the frame to code. The coding mode selection enables competition between direct copy of the prediction or transmission through CodecNet.

The proposed coding scheme is assessed under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding conditions, where it is shown to perform on par with the state-of- the-art video codec ITU/MPEG HEVC. Moreover, the possibility of copying the prediction enables to learn the optical flow in an end-to-end fashion i.e. without relying on pre-training and/or a dedicated loss term.

Other papers relevant for AIVC