Prune Truong

GLU-Net: Global-Local Universal Network for dense flow and correspondences

CVPR 2020 - ORAL

Prune Truong                          Martin Danelljan                          Radu Timofte


                 Paper                                  Code                                  Poster                                  Oral Video                                  Teaser Video                                  Slides                

glunet
GLU-Net architecture

Abstract

Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences. While these applications share fundamental challenges, such as large displacements, pixel-accuracy, and appearance changes, they are currently addressed with specialized network architectures, designed for only one particular task. This severely limits the generalization capabilities of such networks to new scenarios, where e.g. robustness to larger displacements or higher accuracy is required.

In this work, we propose a universal network architecture that is directly applicable to all the aforementioned dense correspondence problems. We achieve both high accuracy and robustness to large displacements by investigating the combined use of global and local correlation layers. We further propose an adaptive resolution strategy, allowing our network to operate on virtually any input image resolution. The proposed GLU-Net achieves state-of-the-art performance for geometric and semantic matching as well as optical flow, when using the same network and weights. Code and trained models are available here.

Visual Results:

  • Aligning images of the ETH3D dataset

Here, we warp the source images toward the target image. We compare our GLU-Net to state-of-the-art optical flow method PWC-Net and geometric matching method DGC-Net.

Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
  • Aligning images of the HPatches dataset (homography dataset)

Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
Source images
Target image
GLU-Net (Ours)
PWC-Net
DGC-Net
  • Aligning images of the semantic matching dataset TSS

TSS more

How to cite:

@inproceedings{GLUNet_Truong_2020,
      title = {{GLU-Net}: Global-Local Universal Network for dense flow and correspondences},
      author    = {Prune Truong and
                   Martin Danelljan and
                   Radu Timofte},
      year = {2020},
      booktitle = {2020 {IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020}
}
© Prune Truong 2020