# Anisotropic Pooling for LUT-realizable CNN Image Restoration

arXiv: https://arxiv.org/abs/2510.21437 · HTML: https://mlsanity.com/paper/2510.21437/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 24 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [Compression Artifacts Reduction by a Deep Convolutional Network](https://mlsanity.com/paper/1504.06993/) (2015)
- [VmambaIR: Visual State Space Model for Image Restoration](https://mlsanity.com/paper/2403.11423/) (2024)
- [Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2207.12987/) (2022)
- [Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton](https://mlsanity.com/paper/2103.15368/) (2021)
- [Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2307.08544/) (2023)
- [Multi-modality Deep Restoration of Extremely Compressed Face Videos](https://mlsanity.com/paper/2107.05548/) (2021)
- [Taming Lookup Tables for Efficient Image Retouching](https://mlsanity.com/paper/2403.19238/) (2024)
- [Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables](https://mlsanity.com/paper/2303.14506/) (2023)
- [DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables](https://mlsanity.com/paper/2503.15931/) (2025)
- [Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression](https://mlsanity.com/paper/2411.16119/) (2024)
- [AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning](https://mlsanity.com/paper/2503.01565/) (2025)

## Abstract (arXiv)

Table look-up realization of image restoration CNNs has the potential of achieving competitive image quality while being much faster and resource frugal than the straightforward CNN implementation. The main technical challenge facing the LUT-based CNN algorithm designers is to manage the table size without overly restricting the receptive field. The prevailing strategy is to reuse the table for small pixel patches of different orientations (apparently assuming a degree of isotropy) and then fuse the look-up results. The fusion is currently done by average pooling, which we find being ill suited to anisotropic signal structures. To alleviate the problem, we investigate and discuss anisotropic pooling methods to replace naive averaging for improving the performance of the current LUT-realizable CNN restoration methods. First, we introduce the method of generalized median pooling which leads to measurable gains over average pooling. We then extend this idea by learning data-dependent pooling coefficients for each orientation, so that they can adaptively weigh the contributions of differently oriented pixel patches. Experimental results on various restoration benchmarks show that our anisotropic pooling strategy yields both perceptually and numerically superior results compared to existing LUT-realizable CNN methods.