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

arXiv: https://arxiv.org/abs/2103.15368 · HTML: https://mlsanity.com/paper/2103.15368/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 59 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Cascaded Partial Decoder for Fast and Accurate Salient Object Detection](https://mlsanity.com/paper/1904.08739/) (2019)
- [A Simple Pooling-Based Design for Real-Time Salient Object Detection](https://mlsanity.com/paper/1904.09569/) (2019)
- [Multi-scale Interactive Network for Salient Object Detection](https://mlsanity.com/paper/2007.09062/) (2020)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [Full Resolution Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1608.05148/) (2016)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations](https://mlsanity.com/paper/1704.00648/) (2017)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [Conditional Probability Models for Deep Image Compression](https://mlsanity.com/paper/1801.04260/) (2018)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Label Decoupling Framework for Salient Object Detection](https://mlsanity.com/paper/2008.11048/) (2020)
- [Weakly-Supervised Salient Object Detection via Scribble Annotations](https://mlsanity.com/paper/2003.07685/) (2020)
- [Towards High-Resolution Salient Object Detection](https://mlsanity.com/paper/1908.07274/) (2019)
- [Learning Convolutional Networks for Content-weighted Image Compression](https://mlsanity.com/paper/1703.10553/) (2017)
- [Learning to Detect](https://mlsanity.com/paper/1805.07631/) (2018)
- [Quantization Guided JPEG Artifact Correction](https://mlsanity.com/paper/2004.09320/) (2020)
- [Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground](https://mlsanity.com/paper/1803.06091/) (2018)
- [Deep Generative Adversarial Compression Artifact Removal](https://mlsanity.com/paper/1704.02518/) (2017)

## Built on by (most cited first, 16 of 16)

- [LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression](https://mlsanity.com/paper/2304.12319/) (2023)
- [LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Network](https://mlsanity.com/paper/2112.06417/) (2021)
- [Content-oriented learned image compression](https://mlsanity.com/paper/2207.14168/) (2022)
- [Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression](https://mlsanity.com/paper/2411.16119/) (2024)
- [Disparity-based Stereo Image Compression with Aligned Cross-View Priors](https://mlsanity.com/paper/2212.00459/) (2022)
- [Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement](https://mlsanity.com/paper/2408.02966/) (2024)
- [DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression](https://mlsanity.com/paper/2412.00437/) (2024)
- [Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion](https://mlsanity.com/paper/2302.06096/) (2023)
- [Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks](https://mlsanity.com/paper/2510.10522/) (2025)
- [BADiff: Bandwidth Adaptive Diffusion Model](https://mlsanity.com/paper/2510.21366/) (2025)
- [DeepFGS: Fine-Grained Scalable Coding for Learned Image Compression](https://mlsanity.com/paper/2201.01173/) (2022)
- [FLLIC: Functionally Lossless Image Compression](https://mlsanity.com/paper/2401.13616/) (2024)
- [Anisotropic Pooling for LUT-realizable CNN Image Restoration](https://mlsanity.com/paper/2510.21437/) (2025)
- [HyperVQ: Enabling Hyperprior Entropy Modeling for VQ-Based Generative Image Compression](https://mlsanity.com/paper/2512.07192/) (2025)
- [Deep Light Pollution Removal in Night Cityscape Photographs](https://mlsanity.com/paper/2604.09145/) (2026)
- [LongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language Models](https://mlsanity.com/paper/2607.01086/) (2026)

## 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.