Quantum Annealing for Computer Vision minimization problems

• Published in: Future generation computer systems 2024-11, Vol.160, p.54-64
• Main Authors: Heidari, Shahrokh, Dinneen, Michael J., Delmas, Patrice
• Format: Article
• Language: English
• Subjects: Computer Vision; Discrete Minimization Models; Quantum Annealing; Quantum Computer Vision; Stereo Matching
• ISSN: 0167-739X
• DOI: 10.1016/j.future.2024.05.037

Computer Vision (CV) labeling problems play a pivotal role in low-level vision. For decades, it has been known that these problems can be elegantly formulated as discrete energy-minimization problems derived from probabilistic graphical models such as Markov Random Fields (MRFs). Despite recent advances in MRF inference algorithms (such as graph-cut and message-passing methods), the resulting energy-minimization problems are generally viewed as intractable. The emergence of quantum computations, which offer the potential for faster solutions to certain problems than classical methods, has led to an increased interest in utilizing quantum properties to overcome intractable problems. Recently, there has also been a growing interest in Quantum Computer Vision (QCV), hoping to provide a credible alternative/assistant to deep learning solutions. This study investigates a new Quantum Annealing-based inference algorithm for CV discrete energy minimization problems. Our contribution is focused on Stereo Matching as a significant CV labeling problem. As a proof of concept, we also use a hybrid quantum–classical solver provided by D-Wave System to compare our results with the best classical inference algorithms in the literature. Our results show that Quantum Annealing can yield promising results for Stereo Matching problems, with improved accuracy on certain stereo images and competitive performance on others. •A Quantum Annealing model (QUBO) to represent any Computer Vision labeling problem.•Proof of correctness and determining lower bounds for the model parameters.•Testing and Analyzing the model on Stereo Matching as one of the most complex Computer Vision labeling problems.•Improved qubit complexity.•Detailed comparison with state-of-the-art Computer Vision iterative minimization algorithms.