• Home
  • Search
  • Coarse-to-Fine PatchMatch for Dense Correspondence
  • Cite Icon25
  • https://doi.org/10.1109/tcsvt.2017.2720175Copy DOI Icon

Coarse-to-Fine PatchMatch for Dense Correspondence

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Although the matching technique has been studied in various areas of computer vision for decades, efficient dense correspondence remains an open problem. In this paper, we present a simple but powerful matching method that works in a coarse-to-fine scheme for optical flow and stereo matching. Inspired by the nearest neighbor field (NNF) algorithms, our approach, called coarse-to-fine PatchMatch, blends an efficient random search strategy with the coarse-to-fine scheme for efficient dense correspondence. Unlike existing NNF techniques, which are efficient but yield results that are often too noisy because of a lack of global regularization, we propose a propagation step involving a constrained random search radius between adjacent levels of a hierarchical architecture. The resulting correspondence has a built-in smoothing effect, making it more suited to dense correspondence than the NNF techniques. Furthermore, our approach can also capture tiny structures with large motions, which is a problem for traditional coarse-to-fine methods. Interpolated using an edge-preserving interpolation method, our method outperforms the state-of-the-art optical flow methods on the MPI-Sintel and KITTI data sets and is much faster than competing methods.

Similar Papers
  • Conference Article
  • Citations1

Autonomous, Bio-inspired vision-based navigation system for indoor flying using hybrid optical flow and stereopsis methods

  • May 17, 2022
  • Masoud Mohtadifar +1
  • Research Article
  • Citations14

Accurate inverse-consistent symmetric optical flow for 4D CT lung registration

  • Sep 25, 2015
  • Biomedical Signal Processing and Control
  • Zhulou Cao +4
  • PDF
  • Research Article
  • Citations22

Intra-aneurysmal flow patterns: illustrative comparison among digital subtraction angiography, optical flow, and computational fluid dynamics.

  • Jul 31, 2014
  • American Journal of Neuroradiology
  • O Brina +10
  • PDF
  • Research Article
  • Citations7

Gas–Liquid Two-Phase Flow Measurement Based on Optical Flow Method with Machine Learning Optimization Model

  • Apr 26, 2024
  • Applied Sciences
  • Junxian Wang +3
  • Research Article
  • Citations6

Typhoon Cloud System Identification and Forecasting Using the Feng-Yun 4A/Advanced Geosynchronous Radiation Imager Based on an Improved Fuzzy Clustering and Optical Flow Method

  • Jul 31, 2019
  • Advances in Meteorology
  • Gen Wang +3
  • Conference Article
  • Citations9

Gesture motion detection algorithm based on optical flow method

  • Oct 01, 2015
  • Yao Lyu +2
  • PDF
  • Research Article
  • Citations3

Study on video key frame extraction in different scenes based on optical flow

  • Dec 01, 2023
  • Journal of Physics: Conference Series
  • Jinshan Dong
  • Research Article
  • Citations36

Analysis of the Velocity Field of CMEs Using Optical Flow Methods

  • Dec 01, 2006
  • The Astrophysical Journal
  • Robin C Colaninno +1
  • Research Article
  • Citations3

Optical flow method for neutron radiography flow diagnostics

  • Oct 01, 2021
  • Physics of Fluids
  • Tianshu Liu +3
  • Conference Article
  • Citations25

Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion

  • Jun 01, 2021
  • Cheng Chi +4
  • Research Article

ИССЛЕДОВАНИЕ МЕТОДА ОПТИЧЕСКОГО ПОТОКА ДЛЯ ДЕТЕКЦИИ ИЗМЕНЕНИЯ РАКУРСА СЪЕМКИ С ВИДЕОКАМЕР В УСЛОВИЯХ ГОРОДСКОЙ СРЕДЫ

  • Jan 01, 2025
  • Herald of Technological University
  • R.N Minnikhanov +5
  • Research Article
  • Citations134

Horn-Schunck Optical Flow with a Multi-Scale Strategy

  • Jul 19, 2013
  • Image Processing On Line
  • Enric Meinhardt-Llopis +2
  • Research Article
  • Citations14

Learning generalized visual odometry using position-aware optical flow and geometric bundle adjustment

  • Dec 15, 2022
  • Pattern Recognition
  • Yi-Jun Cao +6
  • Research Article
  • Citations49

MRI monitoring of laser ablation using optical flow.

  • Nov 01, 1998
  • Journal of Magnetic Resonance Imaging
  • Gary P Zientara +6
  • Research Article
  • Citations8

Synthetic data generation for optical flow evaluation in the neurosurgical domain

  • Aug 01, 2021
  • Current Directions in Biomedical Engineering
  • Markus Philipp +10
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.