paper-with-me

Papers

Generative Visual Compression: A Review

2024-02-03 · Bolin Chen, Shanzhi Yin, Peilin Chen, Shiqi Wang, Yan Ye

Artificial Intelligence Generated Content (AIGC) is leading a new technical revolution for the acquisition of digital content and impelling the progress of visual compression towards competitive performance gains and diverse functionalities over traditional codecs. This paper provides a thorough review on the recent advances of generative visual compression, illustrating great potentials and promising applications in ultra-low bitrate communication, user-specified reconstruction/filtering, and intelligent machine analysis. In particular, we review the visual data compression methodologies with deep generative models, and summarize how compact representation and high-fidelity reconstruction could be actualized via generative techniques. In addition, we generalize related generative compression technologies for machine vision and intelligent analytics. Finally, we discuss the fundamental challenges on generative visual compression techniques and envision their future research directions.

📄 PDF Abstract BibTeX arXiv:2402.02140

Code (0)

등록된 구현이 없습니다.

Tasks

Data Compression

Similar Papers 제목 키워드 기반

Advances in Diffusion-Based Generative Compression

2026-01-26 · Yibo Yang, Stephan Mandt arxiv

Popularized by their strong image generation performance, diffusion and related methods for generative modeling have found widespread success in visual media applications. In particular, diffusion methods have enabled ne…

Image CompressionImage Generation

An Introduction to Neural Data Compression

2022-02-14 · Yibo Yang, Stephan Mandt, Lucas Theis

Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allo…

BIG-bench Machine LearningData CompressionImage Quality Assessment

Generative Compression

2017-03-04 · Shibani Santurkar, David Budden, Nir Shavit

Traditional image and video compression algorithms rely on hand-crafted encoder/decoder pairs (codecs) that lack adaptability and are agnostic to the data being compressed. Here we describe the concept of generative comp…

DecoderVideo Compression

Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models

2026-03-08 · Zongyu Guo, Jiajun He, Zhaoyang Jia, Xiaoyi Zhang 외 arxiv

Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixels, latents, or tokens) remain external to the model and cannot directly exploi…

CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension

2026-02-22 · Lihao Liu, Yan Wang, Biao Yang, Da Li 외 arxiv

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retr…

Visual Question Answering