# LAConv: Local Adaptive Convolution for Image Fusion

arXiv: https://arxiv.org/abs/2107.11617 · HTML: https://mlsanity.com/paper/2107.11617/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 24 Jul 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [Dynamic Region-Aware Convolution](https://mlsanity.com/paper/2003.12243/) (2020)
- [DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks](https://mlsanity.com/paper/2004.10694/) (2020)
- [Pansharpening via Detail Injection Based Convolutional Neural Networks](https://mlsanity.com/paper/1806.08898/) (2018)
- [Fast Fusion of Multi-Band Images Based on Solving a Sylvester Equation](https://mlsanity.com/paper/1502.03121/) (2015)
- [Remote Sensing Image Fusion Based on Two-stream Fusion Network](https://mlsanity.com/paper/1711.02549/) (2017)

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

- [TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing](https://mlsanity.com/paper/2203.10489/) (2022)

## Abstract (arXiv)

The convolution operation is a powerful tool for feature extraction and plays a prominent role in the field of computer vision. However, when targeting the pixel-wise tasks like image fusion, it would not fully perceive the particularity of each pixel in the image if the uniform convolution kernel is used on different patches. In this paper, we propose a local adaptive convolution (LAConv), which is dynamically adjusted to different spatial locations. LAConv enables the network to pay attention to every specific local area in the learning process. Besides, the dynamic bias (DYB) is introduced to provide more possibilities for the depiction of features and make the network more flexible. We further design a residual structure network equipped with the proposed LAConv and DYB modules, and apply it to two image fusion tasks. Experiments for pansharpening and hyperspectral image super-resolution (HISR) demonstrate the superiority of our method over other state-of-the-art methods. It is worth mentioning that LAConv can also be competent for other super-resolution tasks with less computation effort.