paper-with-me

Papers

Perceptually Optimizing Deep Image Compression

2020-07-03 · Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin, Alan C. Bovik

Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess visual information loss, these simple norms are not highly consistent with human perception. Here, we propose a different proxy approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, which mimics the perceptual model while serving as a loss layer of the network.We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of a modern deep image compression models, we are able to demonstrate an averaged bitrate reduction of $28.7\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.

📄 PDF Abstract BibTeX arXiv:2007.02711

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Similar Papers 제목 키워드 기반

Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

2019-10-18 · Simran Kaur, Jeremy Cohen, Zachary C. Lipton

For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the original image. However, Santurkar et al. (2…

Adversarial Robustness

Human Perceptual Evaluations for Image Compression

2019-08-09 · Yash Patel, Srikar Appalaraju, R. Manmatha

Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG20…

Deep LearningImage CompressionMS-SSIMSSIM

Learned HDR Image Compression for Perceptually Optimal Storage and Display

2024-07-18 · Peibei Cao, Haoyu Chen, Jingzhe Ma, Yu-Chieh Yuan 외

High dynamic range (HDR) capture and display have seen significant growth in popularity driven by the advancements in technology and increasing consumer demand for superior image quality. As a result, HDR image compressi…

Image CompressionImage Reconstruction

Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton

2021-03-29 · CVPR 2021 1 · Xi Zhang, Xiaolin Wu

We propose a deep learning system for attention-guided dual-layer image compression (AGDL). In the AGDL compression system, an image is encoded into two layers, a base layer and an attention-guided refinement layer. Unli…

Compressive SensingImage Compression

Learning Perceptual Representations for Gaming NR-VQA with Multi-Task FR Signals

2026-02-12 · Yu-Chih Chen, Michael Wang, Chieh-Dun Wen, Kai-Siang Ma 외 arxiv

No-reference video quality assessment (NR-VQA) for gaming videos is challenging due to limited human-rated datasets and unique content characteristics including fast motion, stylized graphics, and compression artifacts. …

Video Quality AssessmentMulti-Task Learning