jun-pu/awesome-quantum-computer-vision

A curated list of researches in quantum computer vision

Awesome quantum computer vision (Q-CV)

The paper list and the survey paper will be continually updated. Stay tuned!

< Last updated: Aug/21/2023 >

Table of Contents

1. Methodologies
   • Year 2023
   • Year 2022
   • Year 2021
   • Year 2020
2. Contact

Methodologies

Year 2023

Year	Publication	Title	Preprint	Project Page	Key Concepts
2023	ICLR	QuAnt: Quantum Annealing with Learnt Couplings QuAnt: Proposing to learn quadratic unconstrained binary optimization (QUBO) forms from data through gradient back-propagation instead of deriving them. Demonstrating the advantages of learned QUBOs on the diverse problem types of graph matching, 2D point cloud alignment and 3D rotation estimation.	arXiv	Link	Graph Matching, 2D Point Cloud Alignment and 3D Rotation Estimation
2023	CVPR	CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes CCuantuMM: Introducing the first quantum-hybrid cycle-consistent approach for 3D shape multi-matching. Significantly outperforming extensions to multi-shape matching of a previous quantum-hybrid two-shape matching method and is on-par with classical multi-matching methods.	arXiv	Link	3D Shape Matching
2023	CVPR	Quantum Multi Model Fitting QMMF: Formulating multi-model fitting as a problem that can be efficiently sampled by modern adiabatic quantum computers without the relaxation of the objective function. Supporting real-world-sized problems.	arXiv	Link	Geometric Model Fitting
2023	ICML	A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer HHNN: Proposing a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing.	arXiv	Link	Hadamard Product, Convolutional Neural Networks

Year 2022

Year	Publication	Title	Preprint	Project Page	Key Concepts
2022	CVPR	An Iterative Quantum Approach for Transformation Estimation from Point Sets IQT: Proposing an iterative method for estimating rigid transformations from point sets using adiabatic quantum computation.			Transformation Estimation from Point Sets
2022	CVPR	Adiabatic Quantum Computing for Multi Object Tracking AQC-MOT: Proposing the first multi-object tracking formulation designed to be solved with adiabatic quantum computing.	arXiv		Multi-Object Tracking
2022	CVPR	A Hybrid Quantum-Classical Algorithm for Robust Fitting HQC-RF: Novel robust fitting formulation that solves a sequence of integer programs and terminates with a global solution or an error bound.	arXiv		Geometric Model Fitting
2022	ECCV	Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization Q-FW: A hybrid classical-quantum framework based on the Frank-Wolfe algorithm, namely Q-FW, for solving quadratic, linearly-constrained, binary optimization problems on quantum annealers.	arXiv		Frank–Wolfe Algorithm
2022	ECCV	Quantum Motion Segmentation QuMoSeg: The first algorithm for motion segmentation that relies on adiabatic quantum optimization of the objective function.	arXiv	Link	Motion Segmentation

Year 2021

Year	Publication	Title	Preprint	Project Page	Key Concepts
2021	CVPR	Quantum Permutation Synchronization QuantumSync: The first quantum algorithm for solving a synchronization problem in the context of computer vision.	arXiv	Link	Permutation Synchronization
2021	ICCV	Q-Match: Iterative Shape Matching via Quantum Annealing Q-Match: A new iterative quantum method for quadratic assignment problems inspired by the α-expansion algorithm, which allows solving problems of an order of magnitude larger than current quantum methods.	arXiv	Link	3D Shape Matching

Year 2020

Year	Publication	Title	Preprint	Project Page	Key Concepts
2020	NeurIPS	Recurrent Quantum Neural Networks QRNN: Constructing a quantum recurrent neural network (QRNN) with demonstrable performance on non-trivial tasks such as sequence learning and integer digit classification.	arXiv		Recurrent Neural Networks
2020	3DV	Adiabatic Quantum Graph Matching with Permutation Matrix Constraints QGM: Proposing several reformulations of quadratic assignment problems as unconstrained problems suitable for efficient execution on quantum hardware.	arXiv	Link	3D Shape Matching
2020	ECCV	Quantum-soft QUBO Suppression for Accurate Object Detection QSQS: Mapping the task of removing redundant detections into Quadratic Unconstrained Binary Optimization (QUBO) framework that consists of detection score from each bounding box and overlap ratio between pair of bounding boxes. Solve the QUBO problem using the proposed Quantum-soft QUBO Suppression (QSQS) algorithm for fast and accurate detection by exploiting quantum computing advantages.	arXiv		Object Detection

Year 2019

Year	Publication	Title	Preprint	Project Page	Key Concepts
2019	Nature	Supervised learning with quantum-enhanced feature spaces Q-KFs: One method, the quantum variational classifier, uses a variational quantum circuit to classify the data in a way similar to the method of conventional SVMs. The other method, a quantum kernel estimator, estimates the kernel function on the quantum computer and optimizes a classical SVM.	arXiv		Support Vector Machines

Year 2011

Year	Publication	Title	Preprint	Project Page	Key Concepts
2011	ICCVw	The Wave Kernel Signature: A Quantum Mechanical Approach to Shape Analysis WKS: Characterizing points on non-rigid three-dimensional shapes.			Heat Kernel Signature

Contact

Feel free to drop an e-mail to [email protected].