arXiv:2402.11164
TinyLIC-High efficiency lossy image compression method
원문 초록
Image compression has been the subject of extensive research for several decades, resulting in the development of well-known standards such as JPEG, JPEG2000, and H.264/AVC. However, recent advancements in deep learning have led to the emergence of learned image compression methods that offer significant improvements in coding efficiency compared to traditional codecs. These learned compression techniques have shown noticeable gains and even outperformed traditional schemes
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Perception-Oriented Latent Coding for High-Performance Compressed Domain Semantic Inference
NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
DiffO: Single-step Diffusion for Image Compression at Ultra-Low Bitrates
ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
Flexible Mixed Precision Quantization for Learned Image Compression
Structured Pruning and Quantization for Learned Image Compression
토론
이 논문과 연결된 포럼 글이 아직 없습니다.