# Cross-Scale Cost Aggregation for Stereo Matching

arXiv: https://arxiv.org/abs/1403.0316 · HTML: https://mlsanity.com/paper/1403.0316/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2014.

## Built on by (most cited first, 5 of 5)

- [CATs++: Boosting Cost Aggregation with Convolutions and Transformers](https://mlsanity.com/paper/2202.06817/) (2022)
- [Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation](https://mlsanity.com/paper/2203.10291/) (2022)
- [Stereo Matching Based on Visual Sensitive Information](https://mlsanity.com/paper/2105.10831/) (2021)
- [These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusion](https://mlsanity.com/paper/2411.03717/) (2024)
- [Light Field Depth Estimation via Stitched Epipolar Plane Images](https://mlsanity.com/paper/2203.15201/) (2022)

## Abstract (arXiv)

Human beings process stereoscopic correspondence across multiple scales. However, this bio-inspiration is ignored by state-of-the-art cost aggregation methods for dense stereo correspondence. In this paper, a generic cross-scale cost aggregation framework is proposed to allow multi-scale interaction in cost aggregation. We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels. Then, an inter-scale regularizer is introduced into optimization and solving this new optimization problem leads to the proposed framework. Since the regularization term is independent of the similarity kernel, various cost aggregation methods can be integrated into the proposed general framework. We show that the cross-scale framework is important as it effectively and efficiently expands state-of-the-art cost aggregation methods and leads to significant improvements, when evaluated on Middlebury, KITTI and New Tsukuba datasets.