Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 44 of its 74 references that are in the map. First posted on arXiv 13 Feb 2023.
Builds on
44 of 74 references.
References · 44
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2022Generative Adversarial Networkscited by 5,603
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2018Variational image compression with a scale hyperpriorcited by 910
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
- 2018Residual Dense Network for Image Super-Resolutioncited by 796
- 2016End-to-end Optimized Image Compressioncited by 673
- 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
32 more
- 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
- 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
- 2017Lossy Image Compression with Compressive Autoencoderscited by 289
- 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
- 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
- 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 168
- 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 149
- 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
- 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
- 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
- 2018Conditional Probability Models for Deep Image Compressioncited by 128
- 2017Real-Time Adaptive Image Compressioncited by 127
- 2019Pixel-Adaptive Convolutional Neural Networkscited by 126
- 2019Variable Rate Deep Image Compression With a Conditional Autoencodercited by 109
- 2020Invertible Image Rescalingcited by 92
- 2017Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networkscited by 91
- 2018Learning Warped Guidance for Blind Face Restorationcited by 87
- 2021Towards Flexible Blind JPEG Artifacts Removalcited by 76
- 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
- 2020Quantization Guided JPEG Artifact Correctioncited by 57
- 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
- 2021Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutioncited by 52
- 2017Deep Generative Adversarial Compression Artifact Removalcited by 37
- 2021Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeletoncited by 16
- 2016One-to-Many Network for Visually Pleasing Compression Artifacts Reductioncited by 15
- 2021Multi-modality Deep Restoration of Extremely Compressed Face Videoscited by 14
- 2016Compression Artifacts Removal Using Convolutional Neural Networkscited by 13
- 2020Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videoscited by 10
- 2015Postprocessing of Compressed Images via Sequential Denoisingcited by 8
- 2018Near-lossless ℓ_∞-constrained Image Decompression via Deep Neural Networkcited by 5
- 2018Nonlinear Prediction of Multidimensional Signals via Deep Regression with Applications to Image Codingcited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 2.
3 papers.