# Spatially adaptive image compression using a tiled deep network

arXiv: https://arxiv.org/abs/1802.02629 · HTML: https://mlsanity.com/paper/1802.02629/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2018.

## Built on by (most cited first, 10 of 10)

- [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://mlsanity.com/paper/2108.09551/) (2021)
- [A Residual Diffusion Model for High Perceptual Quality Codec Augmentation](https://mlsanity.com/paper/2301.05489/) (2023)
- [Neural Data-Dependent Transform for Learned Image Compression](https://mlsanity.com/paper/2203.04963/) (2022)
- [Learned Image Compression for Machine Perception](https://mlsanity.com/paper/2111.02249/) (2021)
- [Joint Image Compression and Denoising via Latent-Space Scalability](https://mlsanity.com/paper/2205.01874/) (2022)
- [Continuous Patch Stitching for Block-wise Image Compression](https://mlsanity.com/paper/2502.16795/) (2025)
- [Deep Selector-JPEG: Adaptive JPEG Image Compression for Computer Vision in Image classification with Human Vision Criteria](https://mlsanity.com/paper/2302.09560/) (2023)
- [Neural Network Assisted Lifting Steps For Improved Fully Scalable Lossy Image Compression in JPEG 2000](https://mlsanity.com/paper/2403.01647/) (2024)
- [AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting](https://mlsanity.com/paper/2605.20820/) (2026)
- [Variable-Rate Deep Image Compression based on Low-Rank Adaptation by Progressive Learning](https://mlsanity.com/paper/2606.16107/) (2026)

## Abstract (arXiv)

Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant spatial bit rate across each image. While entropy coding introduces some spatial variation, traditional codecs have benefited significantly by explicitly adapting the bit rate based on local image complexity and visual saliency. This paper introduces an algorithm that combines deep neural networks with quality-sensitive bit rate adaptation using a tiled network. We demonstrate the importance of spatial context prediction and show improved quantitative (PSNR) and qualitative (subjective rater assessment) results compared to a non-adaptive baseline and a recently published image compression model based on fully-convolutional neural networks.