• Home
  • Search
  • FALQON-MST: A Fully Quantum Framework for Graph Optimization in Vision Systems
  • https://doi.org/10.5220/0014312400004084Copy DOI Icon

FALQON-MST: A Fully Quantum Framework for Graph Optimization in Vision Systems

  • Jan 1, 2026
  • Guilherme Pexe +6 more
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Finding the minimum spanning tree (MST) of a graph is an important task in computer vision, as it enables a sparse and low-cost representation of connectivity among elements (such as superpixels, points, or regions), which is useful for tasks such as segmentation, reconstruction, and clustering. In this work, we propose and evaluate a fully quantum pipeline for computing MSTs using the FALQON algorithm, a feedback-based quantum optimization method that does not require classical optimizers. We construct a Hamiltonian formulation whose ground-state energy encodes the MST of a graph and compare different FALQON strategies: (i) time rescaling (TR-FALQON) and (ii) multi-driver configurations. To avoid domain-specific biases, we adopt graphs with random weights and show that the FALQON variants exhibit significant differences in ground-state fidelity. We discuss the relevance of this approach for computer vision problems that naturally yield graph representations, and experimental results on synthetic instances together with a small demonstrative study on image segmentation illustrate both the potential and the current limitations of the method. Our numerical simulations on randomly weighted graphs show that standard one drive FALQON, although it reduces the expected energy, fails to concentrate amplitude in the MST solution. The multi drive variant succeeds in redistributing probability mass toward the ground state so that the MST appears among the most probable outcomes, and TR FALQON applied over multi drive produces the best results with faster convergence, lower final energy, and the highest solution state probability or fidelity in our tested instances. These improvements were observed on small synthetic graphs, underscoring both the promise of multi drive controls with temporal rescaling and the need for further scaling and hardware validation.

Similar Papers
  • Research Article
  • Citations107

Multi-objective active distribution networks expansion planning by scenario-based stochastic programming considering uncertain and random weight of network

  • Mar 24, 2018
  • Applied Energy
  • Shiwei Xie +6
  • Research Article
  • Citations11

Image segmentation based on the minimum spanning tree with a novel weight

  • Aug 01, 2020
  • Optik
  • Xiaodong Long +1
  • Research Article
  • Citations199

Sparse Representation With Kernels

  • Sep 21, 2012
  • IEEE Transactions on Image Processing
  • Shenghua Gao +2
  • Conference Article

Efficient Visual Information Retrieval using Orthogonal MSTs

  • Jun 01, 2006
  • Proceedings Elmar ...
  • Christos Theoharatos +3
  • Research Article
  • Citations45

Image registration methods in high‐dimensional space

  • Jan 01, 2006
  • International Journal of Imaging Systems and Technology
  • Huzefa Neemuchwala +3
  • Research Article
  • Citations12

Binocular stereo matching algorithm based on MST cost aggregation.

  • Jan 01, 2021
  • Mathematical Biosciences and Engineering
  • Jian Zhang +4
  • Research Article
  • Citations1

The outlier pixel and sub trees that form segments of image

  • Jan 01, 2020
  • IOP Conference Series: Materials Science and Engineering
  • Efron Manik
  • Research Article
  • Citations63

Review and classification of AI-enabled COVID-19 CT imaging models based on computer vision tasks

  • Dec 18, 2021
  • Computers in Biology and Medicine
  • Haseeb Hassan +8
  • Research Article
  • Citations27

Toward designing intelligent PDEs for computer vision: An optimal control approach

  • Oct 11, 2012
  • Image and Vision Computing
  • Risheng Liu +4
  • Conference Article
  • Citations6

Semantic Learning for Audio Applications: A Computer Vision Approach

  • Jul 10, 2006
  • R Sukthankar +2
  • PDF
  • Research Article
  • Citations3

Image Sampling Based on Dominant Color Component for Computer Vision

  • Aug 06, 2023
  • Electronics
  • Saisai Wang +3
  • Conference Article
  • Citations58

Transformer in Computer Vision

  • Sep 24, 2021
  • Jiarui Bi +2
  • Research Article

Masks-to-Skeleton: Multi-View Mask-Based Tree Skeleton Extraction with 3D Gaussian Splatting

  • Jul 11, 2025
  • Sensors (Basel, Switzerland)
  • Xinpeng Liu +4
  • Conference Article
  • Citations2

Enhanced video analysis framework for action detection using deep learning

  • Apr 27, 2021
  • INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING
  • Saylee Begampure +1
  • Research Article

Object Detection Using YOLOv5: A Deep Learning Approach

  • Feb 04, 2025
  • INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
  • Sakshi Thombre
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.