Description of challenge proposal by NCTU: An autoencoder-based image compressor with principle component analysis and soft-bit rate estimation

Chih Peng Chang, David Alexandre, Wen Hsiao Peng, Hsueh-Ming Hang

研究成果: Conference contribution同行評審

摘要

This paper describes the technology proposal by NCTU for learning-based image compression. The selected technologies include an autoencoder that incorporates (1) a principal component analysis (PCA) layer for energy compaction, (2) a uniform, scalar quantizer for lossy compression, (3) a context-adaptive bitplane coder for entropy coding, and (4) a soft-bit-based rate estimator. The PCA layer includes 1×1 eigen kernels derived from the sample covariance of co-located feature samples across channels. The bitplane coder compresses PCA-transformed feature samples based on their quantized, fixed-point representations, of which the soft bits provide a differentiable approximation for context-adaptive rate estimation. The training of our compression system proceeds in two alternating phases: one for updating the rate estimator and the other for fine tuning the autoencoder regularized by the rate estimator. The proposed method outperforms BPG in terms of both PSNR and MS-SSIM. Several bug fixes have been made since the submission of our decoder. This paper presents the up-to-date results.

原文English
主出版物標題Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
發行者IEEE Computer Society
頁面4321-4325
頁數5
ISBN(電子)9781728125060
出版狀態Published - 6月 2019
事件32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019 - Long Beach, United States
持續時間: 16 6月 201920 6月 2019

出版系列

名字IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
2019-June
ISSN(列印)2160-7508
ISSN(電子)2160-7516

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
國家/地區United States
城市Long Beach
期間16/06/1920/06/19

指紋

深入研究「Description of challenge proposal by NCTU: An autoencoder-based image compressor with principle component analysis and soft-bit rate estimation」主題。共同形成了獨特的指紋。

引用此