Image Compression with Encoder-Decoder Matched Semantic Segmentation

TL;DR

This paper introduces EDMS, a layered image compression framework that improves reconstructed image quality by enhancing semantic segmentation accuracy without extra bits, achieving significant bitrate reduction and faster encoding.

Contribution

The paper proposes a novel EDMS framework that matches encoder-decoder semantic segmentation and enhances segmentation accuracy without additional bit transmission.

Findings

Achieves up to 35.31% BD-rate reduction over HEVC-based codec.

Reduces bitrate by 5%.

Saves 24% encoding time.

Abstract

In recent years, layered image compression is demonstrated to be a promising direction, which encodes a compact representation of the input image and apply an up-sampling network to reconstruct the image. To further improve the quality of the reconstructed image, some works transmit the semantic segment together with the compressed image data. Consequently, the compression ratio is also decreased because extra bits are required for transmitting the semantic segment. To solve this problem, we propose a new layered image compression framework with encoder-decoder matched semantic segmentation (EDMS). And then, followed by the semantic segmentation, a special convolution neural network is used to enhance the inaccurate semantic segment. As a result, the accurate semantic segment can be obtained in the decoder without requiring extra bits. The experimental results show that the proposed EDMS framework can get up to 35.31% BD-rate reduction over the HEVC-based (BPG) codec, 5% bitrate, and 24% encoding time saving compare to the state-of-the-art semantic-based image codec.