42 citations · 161 across the 34 of their papers we have counts for
4 papers · 1 filter
Cycle-Consistent Generative Rendering for 2D-3D Modality Translation
Tristan Aumentado-Armstrong, Alex Levinshtein, Stavros Tsogkas +2
For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that l…
Wavelet Flow: Fast Training of High Resolution Normalizing Flows
Jason J. Yu, Konstantinos G. Derpanis, Marcus A. Brubaker
Normalizing flows are a class of probabilistic generative models which allow for both fast density computation and efficient sampling and are effective at modelling complex distrib…
Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness
Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis +1
In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical…
Learning Multi-Scale Photo Exposure Correction
Mahmoud Afifi, Konstantinos G. Derpanis, Björn Ommer +1
Capturing photographs with wrong exposures remains a major source of errors in camera-based imaging. Exposure problems are categorized as either: (i) overexposed, where the camera…