# Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization

arXiv: https://arxiv.org/abs/2403.13030 · HTML: https://mlsanity.com/paper/2403.13030/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [CrowdHuman: A Benchmark for Detecting Human in a Crowd](https://mlsanity.com/paper/1805.00123/) (2018)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [Context-adaptive Entropy Model for End-to-end Optimized Image Compression](https://mlsanity.com/paper/1809.10452/) (2018)
- [Receptive Field Block Net for Accurate and Fast Object Detection](https://mlsanity.com/paper/1711.07767/) (2017)
- [Global Context-Aware Progressive Aggregation Network for Salient Object Detection](https://mlsanity.com/paper/2003.00651/) (2020)
- [Improving Inference for Neural Image Compression](https://mlsanity.com/paper/2006.04240/) (2020)
- [Causal Contextual Prediction for Learned Image Compression](https://mlsanity.com/paper/2011.09704/) (2020)
- [A Unified End-to-End Framework for Efficient Deep Image Compression](https://mlsanity.com/paper/2002.03370/) (2020)
- [Generative Compression](https://mlsanity.com/paper/1703.01467/) (2017)
- [Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression](https://mlsanity.com/paper/1906.10057/) (2019)
- [An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization](https://mlsanity.com/paper/1912.12817/) (2019)
- [A Cross Channel Context Model for Latents in Deep Image Compression](https://mlsanity.com/paper/2103.02884/) (2021)
- [Deep Perceptual Compression](https://mlsanity.com/paper/1907.08310/) (2019)
- [Thousand to One: Semantic Prior Modeling for Conceptual Coding](https://mlsanity.com/paper/2103.07131/) (2021)

## Built on by (most cited first, 4 of 4)

- [3D Gaussian Splatting Data Compression with Mixture of Priors](https://mlsanity.com/paper/2505.03310/) (2025)
- [Compressible and Searchable: AI-native Multi-Modal Retrieval System with Learned Image Compression](https://mlsanity.com/paper/2404.10234/) (2024)
- [Rethinking Learned Image Compression: Context is All You Need](https://mlsanity.com/paper/2407.11590/) (2024)
- [Region-Adaptive Generative Compression with Spatially Varying Diffusion Models](https://mlsanity.com/paper/2604.01122/) (2026)

## Abstract (arXiv)

Learned Image Compression (LIC) has achieved dramatic progress regarding objective and subjective metrics. MSE-based models aim to improve objective metrics while generative models are leveraged to improve visual quality measured by subjective metrics. However, they all suffer from blurring or deformation at low bit rates, especially at below 0.2bpp. Besides, deformation on human faces and text is unacceptable for visual quality assessment, and the problem becomes more prominent on small faces and text. To solve this problem, we combine the advantage of MSE-based models and generative models by utilizing region of interest (ROI). We propose Hierarchical-ROI (H-ROI), to split images into several foreground regions and one background region to improve the reconstruction of regions containing faces, text, and complex textures. Further, we propose adaptive quantization by non-linear mapping within the channel dimension to constrain the bit rate while maintaining the visual quality. Exhaustive experiments demonstrate that our methods achieve better visual quality on small faces and text with lower bit rates, e.g., 0.7X bits of HiFiC and 0.5X bits of BPG.