paper-with-me

Papers

Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks

2020-09-30 · Hanbin Son, Taeoh Kim, Hyeongmin Lee, Sangyoun Lee

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been designed for an end-to-end learning beyond the conventional compression modules. The postprocessing network increases the quality of decoded images using an example-based learning. The compact representation network is learned to reduce the capacity of an input image to reduce the bitrate while keeping the quality of the decoded image. However, these approaches are not compatible with the existing codecs or not optimal to increase the coding efficiency. Specifically, it is difficult to achieve optimal learning in the previous studies using the compact representation network, due to the inaccurate consideration of the codecs. In this paper, we propose a novel standard compatible image compression framework based on Auxiliary Codec Networks (ACNs). ACNs are designed to imitate image degradation operations of the existing codec, which delivers more accurate gradients to the compact representation network. Therefore, the compact representation and the postprocessing networks can be learned effectively and optimally. We demonstrate that our proposed framework based on JPEG and High Efficiency Video Coding (HEVC) standard substantially outperforms existing image compression algorithms in a standard compatible manner.

📄 PDF Abstract BibTeX arXiv:2009.14754

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Similar Papers 제목 키워드 기반

Preprocessing Enhanced Image Compression for Machine Vision

2022-06-12 · Guo Lu, Xingtong Ge, Tianxiong Zhong, Jing Geng 외

Recently, more and more images are compressed and sent to the back-end devices for the machine analysis tasks~(\textit{e.g.,} object detection) instead of being purely watched by humans. However, most traditional or lear…

Image Compressionobject-detectionObject DetectionQuantization

An End-to-End Compression Framework Based on Convolutional Neural Networks

2017-08-02 · Feng Jiang, Wen Tao, Shaohui Liu, Jie Ren 외

Deep learning, e.g., convolutional neural networks (CNNs), has achieved great success in image processing and computer vision especially in high level vision applications such as recognition and understanding. However, i…

DenoisingImage Compression

Leveraging Learned Image Prior for 3D Gaussian Compression

2025-10-16 · Seungjoo Shin, Jaesik Park, Sunghyun Cho arxiv

Compression techniques for 3D Gaussian Splatting (3DGS) have recently achieved considerable success in minimizing storage overhead for 3D Gaussians while preserving high rendering quality. Despite the impressive storage …

Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder

2022-01-27 · Ankur Mali, Alexander Ororbia, Daniel Kifer, Lee Giles

Recent advances in deep learning have led to superhuman performance across a variety of applications. Recently, these methods have been successfully employed to improve the rate-distortion performance in the task of imag…

DecoderImage CompressionMS-SSIMQuantization+1

Enhanced Invertible Encoding for Learned Image Compression

2021-08-08 · Yueqi Xie, Ka Leong Cheng, Qifeng Chen

Although deep learning based image compression methods have achieved promising progress these days, the performance of these methods still cannot match the latest compression standard Versatile Video Coding (VVC). Most o…

Image Compression