Abstract: In response to the Grand Challenge on Neural Network-based Video Coding at ISCAS 2024, this paper proposes a learned hierarchical B-frame coding scheme. Most learned video codecs concentrate ...

Abstract: Motion compensated inter frame prediction is a common component of all video coders and greatly reduces temporal redundancy. With the rise of deep learning-based image and video compression, ...

This repository contains the implementation of the MH-LVC model proposed in the paper "MH-LVC: Multi-Hypothesis Temporal Prediction for Learned Conditional Residual Video Coding", presented at ICCV ...

Our paper has been accepted to ICCV 2025. This repository contains the source code for HyTIP. Please note that we have optimized the training procedure and enhanced HyTIP’s performance beyond the ...