# Widening siamese architectures for stereo matching

arXiv: https://arxiv.org/abs/1711.00499 · HTML: https://mlsanity.com/paper/1711.00499/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2017.

## Built on by (most cited first, 2 of 2)

- [Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets](https://mlsanity.com/paper/2310.00530/) (2023)
- [Sparse 3D Perception for Rose Harvesting Robots: A Two-Stage Approach Bridging Simulation and Real-World Applications](https://mlsanity.com/paper/2508.00900/) (2025)

## Abstract (arXiv)

Computational stereo is one of the classical problems in computer vision. Numerous algorithms and solutions have been reported in recent years focusing on developing methods for computing similarity, aggregating it to obtain spatial support and finally optimizing an energy function to find the final disparity. In this paper, we focus on the feature extraction component of stereo matching architecture and we show standard CNNs operation can be used to improve the quality of the features used to find point correspondences. Furthermore, we propose a simple space aggregation that hugely simplifies the correlation learning problem. Our results on benchmark data are compelling and show promising potential even without refining the solution.