# An efficient and accurate multi-level cascaded recurrent network for stereo matching

## TL;DR

This paper introduces LMCR-Stereo, a fast and accurate network for stereo matching that improves model inference speed without sacrificing accuracy.

## Contribution

The novel LMCR-Stereo network uses a multi-level cascaded recurrent design and adaptive group correlation layers to enhance efficiency and accuracy.

## Key findings

- LMCR-Stereo achieves state-of-the-art disparity estimation accuracy.
- The model inference speed is improved by 46.0% on the SceneFlow test set.
- It also shows a 50.4% speed improvement on the Middlebury benchmark.

## Abstract

With the advent of Transformer-based convolutional neural networks, stereo matching algorithms have achieved state-of-the-art accuracy in disparity estimation. Nevertheless, this method requires much model inference time, which is the main reason limiting its application in many vision tasks and robots. Facing the trade-off problem between accuracy and efficiency, this paper proposes an efficient and accurate multi-level cascaded recurrent network, LMCR-Stereo. To recover the detailed information of stereo images more accurately, we first design a multi-level network to update the difference values in a coarse-to-fine recurrent iterative manner. Then, we propose a new pair of slow-fast multi-stage superposition inference structures to accommodate the differences between different scene data. Besides, to ensure better disparity estimation accuracy with faster model inference speed, we introduce a pair of adaptive and lightweight group correlation layers to reduce the impact of erroneous rectification and significantly improve model inference speed. The experimental results show that the proposed approach achieves a competitive disparity estimation accuracy with a faster model inference speed than the current state-of-the-art methods. Notably, the model inference speed of the proposed approach is improved by 46.0% and 50.4% in the SceneFlow test set and Middlebury benchmark, respectively.