732 citations · 2.1k across the 26 of their papers we have counts for
7 papers · 2 filters
Toward Quantifying Ambiguities in Artistic Images
Xi Wang, Zoya Bylinskii, Aaron Hertzmann +1
It has long been hypothesized that perceptual ambiguities play an important role in aesthetic experience: a work with some ambiguity engages a viewer more than one that does not. H…
Predicting Visual Importance Across Graphic Design Types
Camilo Fosco, Vincent Casser, Amish Kumar Bedi +3
This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along w…
Contact and Human Dynamics from Monocular Video
Davis Rempe, Leonidas J. Guibas, Aaron Hertzmann +3
Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetr…
Transforming and Projecting Images into Class-conditional Generative Networks
Minyoung Huh, Richard Zhang, Jun-Yan Zhu +2
We present a method for projecting an input image into the space of a class-conditional generative neural network. We propose a method that optimizes for transformation to countera…
Neural Contours: Learning to Draw Lines from 3D Shapes
Difan Liu, Mohamed Nabail, Aaron Hertzmann +1
This paper introduces a method for learning to generate line drawings from 3D models. Our architecture incorporates a differentiable module operating on geometric features of the 3…
GANSpace: Discovering Interpretable GAN Controls
Erik Härkönen, Aaron Hertzmann, Jaakko Lehtinen +1
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging,…