paper-with-me

Papers

Neural Image Compression with Quantization Rectifier

2024-03-25 · Wei Luo, Bo Chen

Neural image compression has been shown to outperform traditional image codecs in terms of rate-distortion performance. However, quantization introduces errors in the compression process, which can degrade the quality of the compressed image. Existing approaches address the train-test mismatch problem incurred during quantization, the random impact of quantization on the expressiveness of image features is still unsolved. This paper presents a novel quantization rectifier (QR) method for image compression that leverages image feature correlation to mitigate the impact of quantization. Our method designs a neural network architecture that predicts unquantized features from the quantized ones, preserving feature expressiveness for better image reconstruction quality. We develop a soft-to-predictive training technique to integrate QR into existing neural image codecs. In evaluation, we integrate QR into state-of-the-art neural image codecs and compare enhanced models and baselines on the widely-used Kodak benchmark. The results show consistent coding efficiency improvement by QR with a negligible increase in the running time.

📄 PDF Abstract BibTeX arXiv:2403.17236

Code (0)

등록된 구현이 없습니다.

Tasks

Feature CorrelationImage CompressionImage ReconstructionQuantization

Similar Papers 제목 키워드 기반

Quantize-then-Rectify: Efficient VQ-VAE Training

2025-07-14 · Borui Zhang, Qihang Rao, Wenzhao Zheng, Jie Zhou 외 arxiv

Visual tokenizers are pivotal in multimodal large models, acting as bridges between continuous inputs and discrete tokens. Nevertheless, training high-compression-rate VQ-VAEs remains computationally demanding, often nec…

Soft then Hard: Rethinking the Quantization in Neural Image Compression

2021-04-12 · Zongyu Guo, Zhizheng Zhang, Runsen Feng, Zhibo Chen

Quantization is one of the core components in lossy image compression. For neural image compression, end-to-end optimization requires differentiable approximations of quantization, which can generally be grouped into thr…

Image CompressionQuantization

Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets

2024-02-29 · Fatih Kamisli, Fabien Racape, Hyomin Choi

Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many approaches have been proposed, includin…

Image CompressionQuantizationVideo Compression

Incremental Color Quantization for Color-Vision-Deficient Observers Using Mobile Gaming Data

2018-03-22 · Jose Cambronero, Phillip Stanley-Marbell, Martin Rinard

The sizes of compressed images depend on their spatial resolution (number of pixels) and on their color resolution (number of color quantization levels). We introduce DaltonQuant, a new color quantization technique for i…

Image CompressionQuantization

DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Coding

2024-08-22 · Jooyoung Lee, Se Yoon Jeong, Munchurl Kim

Unlike fixed- or variable-rate image coding, progressive image coding (PIC) aims to compress various qualities of images into a single bitstream, increasing the versatility of bitstream utilization and providing high com…

Quantization