# Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding

## TL;DR

This paper introduces a CNN-based block up-sampling method for intra frame coding that improves compression efficiency by leveraging learned up-sampling and frame-level optimization, achieving significant bitrate reductions.

## Contribution

The paper presents a novel CNN architecture for block up-sampling in intra coding, incorporating multi-scale fusion and residue learning, and integrates it into HEVC for improved compression.

## Key findings

- Achieves 5.5% BD-rate reduction on standard sequences.
- Achieves 9.0% BD-rate reduction on UHD sequences.
- Significantly improves low bit rate compression efficiency.

## Abstract

Inspired by the recent advances of image super-resolution using convolutional neural network (CNN), we propose a CNN-based block up-sampling scheme for intra frame coding. A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution. Different from previous studies on down/up-sampling-based coding, the up-sampling methods in our scheme have been designed by training CNN instead of hand-crafted. We explore a new CNN structure for up-sampling, which features deconvolution of feature maps, multi-scale fusion, and residue learning, making the network both compact and efficient. We also design different networks for the up-sampling of luma and chroma components, respectively, where the chroma up-sampling CNN utilizes the luma information to boost its performance. In addition, we design a two-stage up-sampling process, the first stage being within the block-by-block coding loop, and the second stage being performed on the entire frame, so as to refine block boundaries. We also empirically study how to set the coding parameters of down-sampled blocks for pursuing the frame-level rate-distortion optimization. Our proposed scheme is implemented into the High Efficiency Video Coding (HEVC) reference software, and a comprehensive set of experiments have been performed to evaluate our methods. Experimental results show that our scheme achieves significant bits saving compared with HEVC anchor especially at low bit rates, leading to on average 5.5% BD-rate reduction on common test sequences and on average 9.0% BD-rate reduction on ultra high definition (UHD) test sequences.