3 papers
cs.CV2021
Non-uniform Blur Kernel Estimation via Adaptive Basis Decomposition
Guillermo Carbajal, Patricia Vitoria, Mauricio Delbracio +2
Motion blur estimation remains an important task for scene analysis and image restoration. In recent years, the removal of motion blur in photographs has seen impressive progress i…
cs.CV2018
Psychophysics, Gestalts and Games
José Lezama, Samy Blusseau, Jean-Michel Morel +2
Many psychophysical studies are dedicated to the evaluation of the human gestalt detection on dot or Gabor patterns, and to model its dependence on the pattern and background param…
cs.CV2017
OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning
José Lezama, Qiang Qiu, Pablo Musé +1
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-c…