# Neural Multi-scale Image Compression

arXiv: https://arxiv.org/abs/1805.06386 · HTML: https://mlsanity.com/paper/1805.06386/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 11 of 11)

- [Neural Video Compression with Diverse Contexts](https://mlsanity.com/paper/2302.14402/) (2023)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [DPICT: Deep Progressive Image Compression Using Trit-Planes](https://mlsanity.com/paper/2112.06334/) (2021)
- [ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Training](https://mlsanity.com/paper/2305.02145/) (2023)
- [Scale-arbitrary Invertible Image Downscaling](https://mlsanity.com/paper/2201.12576/) (2022)
- [Estimating the Resize Parameter in End-to-end Learned Image Compression](https://mlsanity.com/paper/2204.12022/) (2022)
- [End-to-End Optimized Image Compression with the Frequency-Oriented Transform](https://mlsanity.com/paper/2401.08194/) (2024)
- [Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Coding](https://mlsanity.com/paper/2403.05937/) (2024)
- [Window-based Channel Attention for Wavelet-enhanced Learned Image Compression](https://mlsanity.com/paper/2409.14090/) (2024)
- [Deeply-Conditioned Image Compression via Self-Generated Priors](https://mlsanity.com/paper/2510.24437/) (2025)
- [Hadamard-Domain Model Quantization for Learned Image Coding](https://mlsanity.com/paper/2608.01653/) (2026)

## Abstract (arXiv)

This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables and the parallel multi-scale lossless coder enables rapid and accurate lossless coding of the quantized variables via encoding/decoding the variables in parallel. Our proposed model achieves comparable performance to the state-of-the-art model on Kodak and RAISE-1k dataset images, and it encodes a PNG image of size 768 × 512 in 70 ms with a single GPU and a single CPU process and decodes it into a high-fidelity image in approximately 200 ms.