mlsanityData to 7 Oct 2026

Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton

arXiv 2103.15368 ↗First posted 29 Mar 2021cs.CV eess.IVcited by 16

Not on the map. Why?

Abstract (arXiv)

We propose a deep learning system for attention-guided dual-layer image compression (AGDL). In the AGDL compression system, an image is encoded into two layers, a base layer and an attention-guided refinement layer. Unlike the existing ROI image compression methods that spend an extra bit budget equally on all pixels in ROI, AGDL employs a CNN module to predict those pixels on and near a saliency sketch within ROI that are critical to perceptual quality. Only the critical pixels are further sampled by compressive sensing (CS) to form a very compact refinement layer. Another novel CNN method is developed to jointly decode the two compression layers for a much refined reconstruction, while strictly satisfying the transmitted CS constraints on perceptually critical pixels. Extensive experiments demonstrate that the proposed AGDL system advances the state of the art in perception-aware image compression.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 37 of its 59 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

37 of 59 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  6. 2018Variational image compression with a scale hyperpriorcited by 910
  7. 2016End-to-end Optimized Image Compressioncited by 673
  8. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  9. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  10. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  11. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  12. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
25 more
  1. 2020Multi-scale Interactive Network for Salient Object Detectioncited by 212
  2. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 211
  3. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  4. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 170
  5. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 168
  6. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 149
  7. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
  8. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  9. 2018Conditional Probability Models for Deep Image Compressioncited by 128
  10. 2017Real-Time Adaptive Image Compressioncited by 127
  11. 2020Label Decoupling Framework for Salient Object Detectioncited by 111
  12. 2020Weakly-Supervised Salient Object Detection via Scribble Annotationscited by 96
  13. 2019Towards High-Resolution Salient Object Detectioncited by 92
  14. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  15. 2018Learning to Detectcited by 60
  16. 2020Quantization Guided JPEG Artifact Correctioncited by 57
  17. 2018Salient Objects in Clutter: Bringing Salient Object Detection to the Foregroundcited by 47
  18. 2017Deep Generative Adversarial Compression Artifact Removalcited by 37
  19. 2016D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Imagescited by 22
  20. 2018DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removalcited by 20
  21. 2018Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reductioncited by 20
  22. 2016One-to-Many Network for Visually Pleasing Compression Artifacts Reductioncited by 15
  23. 2018Near-lossless ℓ_∞-constrained Image Decompression via Deep Neural Networkcited by 5
  24. 2018Nonlinear Prediction of Multidimensional Signals via Deep Regression with Applications to Image Codingcited by 3
  25. 2019Towards Real-Time Automatic Portrait Matting on Mobile Devicescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 4; 2025: 4; 2026: 2.

16 papers.

Sort:

By area:

  1. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  2. 2021LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Networkcited by 12
  3. 2022Content-oriented learned image compressioncited by 12
  4. 2024Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compressioncited by 8
  5. 2022Disparity-based Stereo Image Compression with Aligned Cross-View Priorscited by 6
  6. 2024Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinementcited by 4
  7. 2024DeepFGS: Fine-Grained Scalable Coding for Learned Image Compressioncited by 4
  8. 2023Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversioncited by 3
  9. 2025Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Taskscited by 1
  10. 2025BADiff: Bandwidth Adaptive Diffusion Modelcited by 1
  11. 2022DeepFGS: Fine-Grained Scalable Coding for Learned Image Compressioncited by 0
  12. 2024FLLIC: Functionally Lossless Image Compressioncited by 0
4 more
  1. 2025Anisotropic Pooling for LUT-realizable CNN Image Restorationcited by 0
  2. 2025HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compressioncited by 0
  3. 2026Deep Light Pollution Removal in Night Cityscape Photographscited by 0
  4. 2026LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Modelscited by 0