paper-with-me

Papers

Variable Rate Image Compression via N-Gram Context based Swin-transformer

2025-09-28 · Priyanka Mudgal arxiv

This paper presents an N-gram context-based Swin Transformer for learned image compression. Our method achieves variable-rate compression with a single model. By incorporating N-gram context into the Swin Transformer, we overcome its limitation of neglecting larger regions during high-resolution image reconstruction due to its restricted receptive field. This enhancement expands the regions considered for pixel restoration, thereby improving the quality of high-resolution reconstructions. Our method increases context awareness across neighboring windows, leading to a -5.86\% improvement in BD-Rate over existing variable-rate learned image compression techniques. Additionally, our model improves the quality of regions of interest (ROI) in images, making it particularly beneficial for object-focused applications in fields such as manufacturing and industrial vision systems.

📄 PDF Abstract BibTeX arXiv:2510.00058

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionImage Compression

Similar Papers 제목 키워드 기반

GOLLIC: Learning Global Context beyond Patches for Lossless High-Resolution Image Compression

2022-10-07 · Yuan Lan, Liang Qin, Zhaoyi Sun, Yang Xiang 외

Neural-network-based approaches recently emerged in the field of data compression and have already led to significant progress in image compression, especially in achieving a higher compression ratio. In the lossless ima…

ClusteringData CompressionImage Compression

Fully Convolutional Model for Variable Bit Length and Lossy High Density Compression of Mammograms

2018-05-17 · Aupendu Kar, Sri Phani Krishna Karri, Nirmalya Ghosh, Ramanathan Sethuraman 외

Early works on medical image compression date to the 1980's with the impetus on deployment of teleradiology systems for high-resolution digital X-ray detectors. Commercially deployed systems during the period could compr…

Image CompressionSSIM

Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression

2025-03-27 · Hanyue Tu, Siqi Wu, Li Li, Wengang Zhou 외

Autoencoder-based structures have dominated recent learned image compression methods. However, the inherent information loss associated with autoencoders limits their rate-distortion performance at high bit rates and res…

Image Compression

Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression

2022-03-21 · CVPR 2022 1 · Xiaosu Zhu, Jingkuan Song, Lianli Gao, Feng Zheng 외

Modeling latent variables with priors and hyperpriors is an essential problem in variational image compression. Formally, trade-off between rate and distortion is handled well if priors and hyperpriors precisely describe…

Image CompressionQuantization

High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation

2022-09-12 · Shilv Cai, Zhijun Zhang, Liqun Chen, Luxin Yan 외

Learning-based methods have effectively promoted the community of image compression. Meanwhile, variational autoencoder (VAE) based variable-rate approaches have recently gained much attention to avoid the usage of a set…

Image CompressionVocal Bursts Intensity Prediction