F-LIC: FPGA-based Learned Image Compression with a Fine-grained Pipeline

Heming Sun*, Qingyang Yi, Fangzheng Lin, Lu Yu, Jiro Katto, Masahiro Fujita

*この研究の対応する著者

研究成果: Conference contribution

抄録

Recently, learned image compression (LIC) has shown a superior ability in the compression ratio as well as the quality of the reconstructed image. By adopting the framework of variational autoencoder, LIC [1] can outperform the intra prediction of the latest traditional coding standard VVC. To accelerate the coding speed, most LIC frameworks are operated on GPU with the floating-point arithmetic. However, the mismatch of floating-point calculation results on various hardware platforms will cause the decoding error if encoding and decoding are performed on different platforms. Therefore, LIC with a fixed-point arithmetic [2-3] is highly required. This paper gives an FPGA design for a LIC with 8-bit fixed-point quantization. Different from existing FPGA accelerators [4-6], we propose a fine-grained pipeline architecture to realize high DSP efficiency. Cascading DSP and the deconvolution with zero skipping are also developed to enhance the hardware performance.

本文言語English
ホスト出版物のタイトル2022 IEEE Asian Solid-State Circuits Conference, A-SSCC 2022 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781665471435
DOI
出版ステータスPublished - 2022
イベント2022 IEEE Asian Solid-State Circuits Conference, A-SSCC 2022 - Taipei, Taiwan, Province of China
継続期間: 2022 11月 62022 11月 9

出版物シリーズ

名前2022 IEEE Asian Solid-State Circuits Conference, A-SSCC 2022 - Proceedings

Conference

Conference2022 IEEE Asian Solid-State Circuits Conference, A-SSCC 2022
国/地域Taiwan, Province of China
CityTaipei
Period22/11/622/11/9

ASJC Scopus subject areas

  • ハードウェアとアーキテクチャ
  • 信号処理
  • 電子工学および電気工学
  • 安全性、リスク、信頼性、品質管理
  • 器械工学
  • コンピュータ ネットワークおよび通信

フィンガープリント

「F-LIC: FPGA-based Learned Image Compression with a Fine-grained Pipeline」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル