3 papers
eess.IV2020
Optical Flow and Mode Selection for Learning-based Video Coding
Théo Ladune, Pierrick Philippe, Wassim Hamidouche +2
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…
cs.NE2020
ModeNet: Mode Selection Network For Learned Video Coding
Théo Ladune, Pierrick Philippe, Wassim Hamidouche +2
In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression. Inspired by traditional video coding, ModeNet purpose is to enable c…
eess.IV2020
Binary Probability Model for Learning Based Image Compression
Théo Ladune, Pierrick Philippe, Wassim Hamidouche +2
In this paper, we propose to enhance learned image compression systems with a richer probability model for the latent variables. Previous works model the latents with a Gaussian or…