Results 21 to 30 of about 7,136,792 (296)
Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform [PDF]
IEEE International Conference on Computer Vision, 2021 We propose a versatile deep image compression network based on Spatial Feature Transform (SFT) [45], which takes a source image and a corresponding quality map as inputs and produce a compressed image with variable rates. Our model covers a wide range of
Myung-Sin Song +2 more
semanticscholar +1 more source
Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules [PDF]
Computer Vision and Pattern Recognition, 2020 Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results.
Zhengxue Cheng +3 more
semanticscholar +1 more source
Transformer-based Image Compression [PDF]
Data Compression Conference, 2021 A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders [1], as shown in Fig. 1a.
Ming-Tse Lu +4 more
semanticscholar +1 more source
Channel-Wise Autoregressive Entropy Models for Learned Image Compression [PDF]
International Conference on Information Photonics, 2020 In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective learned image codecs take the form of an entropy-constrained autoencoder ...
David C. Minnen, Saurabh Singh
semanticscholar +1 more source
Slimmable Compressive Autoencoders for Practical Neural Image Compression [PDF]
Computer Vision and Pattern Recognition, 2021 Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting ...
Feiyu Yang +3 more
semanticscholar +1 more source
Context-Aware Image Compression. [PDF]
PLoS ONE, 2016 We describe a physics-based data compression method inspired by the photonic time stretch wherein information-rich portions of the data are dilated in a process that emulates the effect of group velocity dispersion on temporal signals.
Jacky C K Chan +3 more
doaj +1 more source
Learned Image Compression With Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules [PDF]
IEEE Transactions on Image Processing, 2021 Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video Coding (VVC) in both PSNR and MS-SSIM metrics.
H. Fu +9 more
semanticscholar +1 more source
Causal Contextual Prediction for Learned Image Compression [PDF]
IEEE transactions on circuits and systems for video technology (Print), 2020 Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent representations and then ...
Zongyu Guo +3 more
semanticscholar +1 more source
Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation [PDF]
Computer Vision and Pattern Recognition, 2020 With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of rate-distortion ...
Ze Cui +5 more
semanticscholar +1 more source
Learning End-to-End Lossy Image Compression: A Benchmark [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020 Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline by ...
Yueyu Hu +3 more
semanticscholar +1 more source