Skip to content
conftrace_
2020 CVPR CVPR 2020

A Quantum Computational Approach to Correspondence Problems on Point Sets

Abstract

Modern adiabatic quantum computers (AQC) are already used to solve difficult combinatorial optimisation problems in various domains of science. Currently, only a few applications of AQC in computer vision have been demonstrated. We review AQC and derive a new algorithm for correspondence problems on point sets suitable for execution on AQC. Our algorithm has a subquadratic computational complexity of the state preparation. Examples of successful transformation estimation and point set alignment by simulated sampling are shown in the systematic experimental evaluation. Finally, we analyse the differences in the solutions and the corresponding energy values.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision and Interdisciplinary
📈 Trend Setter - Quantum Computing
🐣 Hot Topic Early Bird - quantum computing

Authors

Vladislav Golyanik, Christian Theobalt

Topics

Machine Learning > Optimization & Theory > Optimization Deep Learning > Architectures > Graph Neural Networks Computer Vision > Analysis > 3D Vision Interdisciplinary > Science > Quantum Computing Computer Vision > Core AI > Computer Vision

Keywords

combinatorial optimization computer vision quantum computing quantum algorithm combinatorial optimisation 3d registration point set correspondence problem transformation estimation adiabatic quantum computing adiabatic quantum computer point set correspondence
Download PDF

More from CVPR 2020

All CVPR 2020 papers →
Computing Valid P-Values for Image Segmentation by Selective Inference
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images
Scene-Adaptive Video Frame Interpolation via Meta-Learning