paper-with-me

Papers

Memory-Efficient Learned Image Compression with Pruned Hyperprior Module

2022-06-21 · Ao Luo, Heming Sun, Jinming Liu, Jiro Katto

Learned Image Compression (LIC) gradually became more and more famous in these years. The hyperprior-module-based LIC models have achieved remarkable rate-distortion performance. However, the memory cost of these LIC models is too large to actually apply them to various devices, especially to portable or edge devices. The parameter scale is directly linked with memory cost. In our research, we found the hyperprior module is not only highly over-parameterized, but also its latent representation contains redundant information. Therefore, we propose a novel pruning method named ERHP in this paper to efficiently reduce the memory cost of hyperprior module, while improving the network performance. The experiments show our method is effective, reducing at least 22.6% parameters in the whole model while achieving better rate-distortion performance.

📄 PDF Abstract BibTeX arXiv:2206.10083

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Learned Image Compression with Separate Hyperprior Decoders

2021-10-31 · Zhao Zan, Chao Liu, Heming Sun, Xiaoyang Zeng 외

Learned image compression techniques have achieved considerable development in recent years. In this paper, we find that the performance bottleneck lies in the use of a single hyperprior decoder, in which case the ternar…

DecoderImage CompressionMS-SSIMSSIM

Non-local Attention Optimized Deep Image Compression

2019-04-22 · Haojie Liu, Tong Chen, Peiyao Guo, Qiu Shen 외

This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure. Our NLAIC framework embeds non-local oper…

Image CompressionMS-SSIMSSIM

Neural Image Compression via Non-Local Attention Optimization and Improved Context Modeling

2019-10-11 · Tong Chen, Haojie Liu, Zhan Ma, Qiu Shen 외

This paper proposes a novel Non-Local Attention optmization and Improved Context modeling-based image compression (NLAIC) algorithm, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (…

Image CompressionMS-SSIMSSIM

Variational image compression with a scale hyperprior

2018-02-01 · ICLR 2018 · Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang 외

We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies in the latent representation. This hyperp…

Image CompressionMS-SSIMSSIM

CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression

2025-03-01 · Yu-Ting Zhan, Cheng-Yuan Ho, Hebi Yang, Yi-Hsin Chen 외

3D Gaussian Splatting (3DGS) has recently emerged as a promising 3D representation. Much research has been focused on reducing its storage requirements and memory footprint. However, the needs to compress and transmit th…

3DGSImage Compression