# ARCHE: Autoregressive Residual Compression with Hyperprior and Excitation

arXiv: https://arxiv.org/abs/2603.10188 · HTML: https://mlsanity.com/paper/2603.10188/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [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)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [The Devil Is in the Details: Window-based Attention for Image Compression](https://mlsanity.com/paper/2203.08450/) (2022)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks](https://mlsanity.com/paper/1703.10114/) (2017)
- [Non-local Attention Optimized Deep Image Compression](https://mlsanity.com/paper/1904.09757/) (2019)
- [Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation](https://mlsanity.com/paper/2003.02012/) (2020)
- [End-to-end optimization of nonlinear transform codes for perceptual quality](https://mlsanity.com/paper/1607.05006/) (2016)
- [Causal Contextual Prediction for Learned Image Compression](https://mlsanity.com/paper/2011.09704/) (2020)
- [Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression](https://mlsanity.com/paper/2203.02452/) (2022)
- [Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression](https://mlsanity.com/paper/2203.10897/) (2022)
- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [Lossy Image Compression with Quantized Hierarchical VAEs](https://mlsanity.com/paper/2208.13056/) (2022)
- [TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception](https://mlsanity.com/paper/2306.05085/) (2023)
- [Learned Block-based Hybrid Image Compression](https://mlsanity.com/paper/2012.09550/) (2020)
- [Causal Context Adjustment Loss for Learned Image Compression](https://mlsanity.com/paper/2410.04847/) (2024)
- [3-D Context Entropy Model for Improved Practical Image Compression](https://mlsanity.com/paper/2004.08273/) (2020)
- [Boosting Neural Image Compression for Machines Using Latent Space Masking](https://mlsanity.com/paper/2112.08168/) (2021)
- [Generalized Gaussian Model for Learned Image Compression](https://mlsanity.com/paper/2411.19320/) (2024)
- [An Overview of the JPEG AI Learning-Based Image Coding Standard](https://mlsanity.com/paper/2510.13867/) (2025)
- [On Efficient Neural Network Architectures for Image Compression](https://mlsanity.com/paper/2406.10361/) (2024)
- [ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression](https://mlsanity.com/paper/2307.06342/) (2023)

## Abstract (arXiv)

Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However, many existing approaches achieve high rate-distortion efficiency at the expense of increased computational cost and limited parallelism. This paper presents ARCHE - Autoregressive Residual Compression with Hyperprior and Excitation, an end-to-end learned image compression framework that balances modeling accuracy and computational efficiency. The proposed architecture unifies hierarchical, spatial, and channel-based priors within a single probabilistic framework, capturing both global and local dependencies in the latent representation of the image, while employing adaptive feature recalibration and residual refinement to enhance latent representation quality. Without relying on recurrent or transformer-based components, ARCHE attains state-of-the-art rate-distortion efficiency: it reduces the BD-Rate by approximately 48% relative to the commonly used benchmark model of Balle et al., 30% relative to the channel-wise autoregressive model of Minnen & Singh and 5% against the VVC Intra codec on the Kodak benchmark dataset. The framework maintains computational efficiency with 95M parameters and 222ms running time per image. Visual comparisons confirm sharper textures and improved color fidelity, particularly at lower bit rates, demonstrating that accurate entropy modeling can be achieved through efficient convolutional designs suitable for practical deployment.