Paper Reading AI Learner

Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion

2023-02-13 04:36:13
Xi Zhang, Xiaolin Wu

Abstract

Ultra high resolution (UHR) images are almost always downsampled to fit small displays of mobile end devices and upsampled to its original resolution when exhibited on very high-resolution displays. This observation motivates us on jointly optimizing operation pairs of downsampling and upsampling that are spatially adaptive to image contents for maximal rate-distortion performance. In this paper, we propose an adaptive downsampled dual-layer (ADDL) image compression system. In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer. For decompression the base layer is decoded and upconverted to the original resolution using a deep upsampling neural network, aided by the prior knowledge of the learned adaptive downsampling kernels. We restrict the downsampling kernels to the form of Gabor filters in order to reduce the complexity of filter optimization and also reduce the amount of side information needed by the decoder for adaptive upsampling. Extensive experiments demonstrate that the proposed ADDL compression approach of jointly optimized, spatially adaptive downsampling and upconversion outperforms the state of the art image compression methods.

Abstract (translated)

超高清(UHR)图像几乎总是被裁剪以适应移动设备终端设备的小型显示器,并在展示在极高的分辨率显示器上时将其恢复至其原始分辨率。这一观察激励我们共同优化空间自适应裁剪和拉伸操作对,以最大化速率扭曲性能。在本文中,我们提出了一种自适应裁剪两 layer (ADDL)图像压缩系统。在ADDL压缩系统中,图像通过学习内容自适应裁剪kernels进行裁剪,并压缩成编码基层。为了解压,基层通过深度拉伸神经网络解码和恢复至原始分辨率,借助学习自适应裁剪kernels的先前知识。我们限制裁剪kernels以 Gabor 滤波器的形式,以减少滤波优化的复杂性,并减少解码器自适应拉伸所需的 Side Information 数量。广泛的实验表明,提出的ADDL压缩方法,空间自适应裁剪和解码的协同优化,比当前的图像压缩方法更有效。

URL

https://arxiv.org/abs/2302.06096

PDF

https://arxiv.org/pdf/2302.06096.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot