paper-with-me

Papers

LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression

2024-11-20 · Shimon Murai, Heming Sun, Jiro Katto

Supported by powerful generative models, low-bitrate learned image compression (LIC) models utilizing perceptual metrics have become feasible. Some of the most advanced models achieve high compression rates and superior perceptual quality by using image captions as sub-information. This paper demonstrates that using a large multi-modal model (LMM), it is possible to generate captions and compress them within a single model. We also propose a novel semantic-perceptual-oriented fine-tuning method applicable to any LIC network, resulting in a 41.58\% improvement in LPIPS BD-rate compared to existing methods. Our implementation and pre-trained weights are available at https://github.com/tokkiwa/ImageTextCoding.

📄 PDF Abstract BibTeX arXiv:2411.13033

Code (1)

tokkiwa/imagetextcoding 공식 구현 pytorch

Tasks

Image CaptioningImage Compression

Similar Papers 제목 키워드 기반

Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysis

2025-10-31 · Weiming Chen, Yijia Wang, Zhihan Zhu, Zhihai He arxiv

We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication bandwidth, such as deep space exploration…

Text-to-Image GenerationImage ReconstructionImage CompressionRobot Navigation

Taming Large Multimodal Agents for Ultra-low Bitrate Semantically Disentangled Image Compression

2025-03-01 · Juan Song, Lijie Yang, Mingtao Feng

It remains a significant challenge to compress images at ultra-low bitrate while achieving both semantic consistency and high perceptual quality. We propose a novel image compression framework, Semantically Disentangled …

DecoderImage CompressionObject

Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression

2025-05-22 · Linfeng Qi, Zhaoyang Jia, Jiahao Li, Bin Li 외

Most existing approaches for image and video compression perform transform coding in the pixel space to reduce redundancy. However, due to the misalignment between the pixel-space distortion and human perception, such sc…

Image CompressionVideo Compression

Your Demands Deserve More Bits: Referring Semantic Image Compression at Ultra-low Bitrate

2025-05-31 · Chenhao Wu, Qingbo Wu, Haoran Wei, Shuai Chen 외

With the help of powerful generative models, Semantic Image Compression (SIC) has achieved impressive performance at ultra-low bitrate. However, due to coarse-grained visual-semantic alignment and inherent randomness, th…

Image Compression

Low-Rate Semantic Communication with Codebook-based Conditional Generative Models

2025-04-07 · Kailang Ye, Mingze Gong, Shuoyao Wang, Daquan Feng

Generative semantic communication models are reshaping semantic communication frameworks by moving beyond pixel-wise optimization to align with human perception. However, many existing approaches prioritize image-level p…

Saliency DetectionSemantic Communication