# Quantum-Hybrid Stereo Matching With Nonlinear Regularization and Spatial Pyramids

arXiv: https://arxiv.org/abs/2312.16118 · HTML: https://mlsanity.com/paper/2312.16118/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 55 references that are in the map.
- First posted on arXiv 26 Dec 2023.

## Builds on (most cited first, 13 of 13)

- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [A Survey on Deep Learning Techniques for Stereo-based Depth Estimation](https://mlsanity.com/paper/2006.02535/) (2020)
- [AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching](https://mlsanity.com/paper/2004.04627/) (2020)
- [Adversarial Patch Attacks on Monocular Depth Estimation Networks](https://mlsanity.com/paper/2010.03072/) (2020)
- [Q-Match: Iterative Shape Matching via Quantum Annealing](https://mlsanity.com/paper/2105.02878/) (2021)
- [A practical heuristic for finding graph minors](https://mlsanity.com/paper/1406.2741/) (2014)
- [Adiabatic Quantum Computing for Multi Object Tracking](https://mlsanity.com/paper/2202.08837/) (2022)
- [Adiabatic Quantum Graph Matching with Permutation Matrix Constraints](https://mlsanity.com/paper/2107.04032/) (2021)
- [Continuous 3D Label Stereo Matching using Local Expansion Moves](https://mlsanity.com/paper/1603.08328/) (2016)
- [A Hybrid Quantum-Classical Algorithm for Robust Fitting](https://mlsanity.com/paper/2201.10110/) (2022)
- [Quantum Motion Segmentation](https://mlsanity.com/paper/2203.13185/) (2022)
- [Matching Point Sets with Quantum Circuit Learning](https://mlsanity.com/paper/2102.06697/) (2021)
- [Stereo Matching by Joint Energy Minimization](https://mlsanity.com/paper/1601.03890/) (2016)

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

- [Quantum-enhanced Computer Vision: Going Beyond Classical Algorithms](https://mlsanity.com/paper/2510.07317/) (2025)
- [Quantum Multiple Rotation Averaging](https://mlsanity.com/paper/2602.10115/) (2026)

## Abstract (arXiv)

Quantum visual computing is advancing rapidly. This paper presents a new formulation for stereo matching with nonlinear regularizers and spatial pyramids on quantum annealers as a maximum a posteriori inference problem that minimizes the energy of a Markov Random Field. Our approach is hybrid (i.e., quantum-classical) and is compatible with modern D-Wave quantum annealers, i.e., it includes a quadratic unconstrained binary optimization (QUBO) objective. Previous quantum annealing techniques for stereo matching are limited to using linear regularizers, and thus, they do not exploit the fundamental advantages of the quantum computing paradigm in solving combinatorial optimization problems. In contrast, our method utilizes the full potential of quantum annealing for stereo matching, as nonlinear regularizers create optimization problems which are NP-hard. On the Middlebury benchmark, we achieve an improved root mean squared accuracy over the previous state of the art in quantum stereo matching of 2% and 22.5% when using different solvers.