A GAN-based Tunable Image Compression System
The method of importance map has been widely adopted in DNN-based lossy image compression to achieve bit allocation according to the importance of image contents. However, insufficient allocation of bits in non-important regions often leads to severe distortion at low bpp (bits per pixel), which hampers the development of efficient content-weighted image compression systems. This paper rethinks content-based compression by using Generative Adversarial Network (GAN) to reconstruct the non-important regions. Moreover, multiscale pyramid decomposition is applied to both the encoder and the discriminator to achieve global compression of high-resolution images. A tunable compression scheme is also proposed in this paper to compress an image to any specific compression ratio without retraining the model. The experimental results show that our proposed method improves MS-SSIM by more than 10.3% compared to the recently reported GAN-based method to achieve the same low bpp (0.05) on the Kodak dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkImage CompressionMS-SSIMSSIMSimilar Papers 제목 키워드 기반
Mobiprox: Supporting Dynamic Approximate Computing on Mobiles
Runtime-tunable context-dependent network compression would make mobile deep learning (DL) adaptable to often varying resource availability, input "difficulty", or user needs. The existing compression techniques signific…
Activity RecognitionHuman Activity RecognitionA Novel Algorithm for Exact Concave Hull Extraction
Region extraction is necessary in a wide range of applications, from object detection in autonomous driving to analysis of subcellular morphology in cell biology. There exist two main approaches: convex hull extraction, …
Autonomous DrivingData CompressionImage Compressionobject-detection+2Lossless and Near-Lossless Compression for Foundation Models
With the growth of model sizes and scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast literature about reducing mode…
SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression
Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantizatio…
Reconfiguring the Imaging Pipeline for Computer Vision
Advancements in deep learning have ignited an explosion of research on efficient hardware for embedded computer vision. Hardware vision acceleration, however, does not address the cost of capturing and processing the ima…
Demosaicking