Scale Space and Variational Methods in Computer Vision

1. Front Matter

   Pages i-xiv

   PDF

2. Scale Space and Partial Differential Equations Methods

   1. Front Matter

      Pages 1-1

      PDF

   2. Scale-Covariant and Scale-Invariant Gaussian Derivative Networks

      • Tony Lindeberg

      Pages 3-14

   3. Quantisation Scale-Spaces

      • Pascal Peter

      Pages 15-26

   4. Equivariant Deep Learning via Morphological and Linear Scale Space PDEs on the Space of Positions and Orientations

      • Remco Duits, Bart Smets, Erik Bekkers, Jim Portegies

      Pages 27-39

   5. Nonlinear Spectral Processing of Shapes via Zero-Homogeneous Flows

      • Jonathan Brokman, Guy Gilboa

      Pages 40-51

   6. Total-Variation Mode Decomposition

      • Ido Cohen, Tom Berkov, Guy Gilboa

      Pages 52-64

   7. Fast Morphological Dilation and Erosion for Grey Scale Images Using the Fourier Transform

      • Marvin Kahra, Vivek Sridhar, Michael Breuß

      Pages 65-77

   8. Diffusion, Pre-smoothing and Gradient Descent

      • Martin Welk

      Pages 78-90

   9. Local Culprits of Shape Complexity

      • Mazlum Ferhat Arslan, Sibel Tari

      Pages 91-99

   10. Extension of Mathematical Morphology in Riemannian Spaces

       • El Hadji S. Diop, Alioune Mbengue, Bakary Manga, Diaraf Seck

       Pages 100-111

3. Flow, Motion and Registration

   1. Front Matter

      Pages 113-113

      PDF

   2. Multiscale Registration

      • Noémie Debroux, Carole Le Guyader, Luminita A. Vese

      Pages 115-127

   3. Challenges for Optical Flow Estimates in Elastography

      • Ekaterina Sherina, Lisa Krainz, Simon Hubmer, Wolfgang Drexler, Otmar Scherzer

      Pages 128-139

   4. An Anisotropic Selection Scheme for Variational Optical Flow Methods with Order-Adaptive Regularisation

      • Lukas Mehl, Cedric Beschle, Andrea Barth, Andrés Bruhn

      Pages 140-152

   5. Low-Rank Registration of Images Captured Under Unknown, Varying Lighting

      • Matthieu Pizenberg, Yvain Quéau, Abderrahim Elmoataz

      Pages 153-164

   6. Towards Efficient Time Stepping for Numerical Shape Correspondence

      • Alexander Köhler, Michael Breuß

      Pages 165-176

   7. First Order Locally Orderless Registration

      • Sune Darkner, José D. T. Vidarte, François Lauze

      Pages 177-188

4. Optimization Theory and Methods in Imaging

   1. Front Matter

      Pages 189-189

      PDF

   2. First-Order Geometric Multilevel Optimization for Discrete Tomography

      • Jan Plier, Fabrizio Savarino, Michal Kočvara, Stefania Petra

      Pages 191-203

This book constitutes the proceedings of the 8th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2021, which took place during May 16-20, 2021. The conference was planned to take place in Cabourg, France, but changed to an online format due to the COVID-19 pandemic.

The 45 papers included in this volume were carefully reviewed and selected from a total of 64 submissions. They were organized in topical sections named as follows: scale space and partial differential equations methods; flow, motion and registration; optimization theory and methods in imaging; machine learning in imaging; segmentation and labelling; restoration, reconstruction and interpolation; and inverse problems in imaging. 

• communication systems
• computer networks
• computer vision
• correlation analysis
• image analysis
• image processing
• image quality
• image reconstruction
• image segmentation
• inverse problems
• machine learning
• mathematical imaging
• numerical methods
• optimization
• partial differential equations
• pattern recognition
• scale space
• scale-space
• signal processing
• variational methods

• UNICAEN, GREYC – Normandy University, Caen, France

  Abderrahim Elmoataz, Julien Rabin

• ENSICAEN, GREYC – Normandy University, Caen, France

  Jalal Fadili, Loïc Simon

• CNRS, GREYC – Normandy University, Caen, France

  Yvain Quéau

Policies and ethics