# Spatial Competition for Low-Complexity Learned Image Compression

arXiv: https://arxiv.org/abs/2605.13243 · HTML: https://mlsanity.com/paper/2605.13243/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2026.

## Built on by (most cited first, 1 of 1)

- [ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression](https://mlsanity.com/paper/2606.00111/) (2026)

## Abstract (arXiv)

Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a low-complexity learned image compression framework based on spatial competition between multiple specialized neural codecs. For each image region, the encoder selects the codec that best matches the local content according to a rate-distortion cost. A mode map is transmitted as side information to indicate the per-region codec selection. At decoding time, this mode map-based selection guides reconstruction while preserving the complexity of a single codec. This design enables per-image adaptation with low decoding complexity and fast encoding. On the CLIC 2020 dataset, our method achieves up to -14.5% rate reduction compared to a single codec and reaches HEVC-level performance with a decoding complexity of 1433 MACs per pixel.