Search Results for author: Aaron Hertzmann

Found 35 papers, 16 papers with code

Data Attribution for Text-to-Image Models by Unlearning Synthesized Images

1 code implementation13 Jun 2024 Sheng-Yu Wang, Aaron Hertzmann, Alexei A. Efros, Jun-Yan Zhu, Richard Zhang

The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image.

Segmentation-Based Parametric Painting

1 code implementation24 Nov 2023 Manuel Ladron De Guevara, Matthew Fisher, Aaron Hertzmann

We introduce a novel image-to-painting method that facilitates the creation of large-scale, high-fidelity paintings with human-like quality and stylistic variation.


Art and the science of generative AI: A deeper dive

no code implementations7 Jun 2023 Ziv Epstein, Aaron Hertzmann, Laura Herman, Robert Mahari, Morgan R. Frank, Matthew Groh, Hope Schroeder, Amy Smith, Memo Akten, Jessica Fjeld, Hany Farid, Neil Leach, Alex Pentland, Olga Russakovsky

A new class of tools, colloquially called generative AI, can produce high-quality artistic media for visual arts, concept art, music, fiction, literature, video, and animation.

Towards Better User Studies in Computer Graphics and Vision

no code implementations23 Jun 2022 Zoya Bylinskii, Laura Herman, Aaron Hertzmann, Stefanie Hutka, Yile Zhang

We discuss foundational user research methods (e. g., needfinding) that are presently underutilized in computer vision and graphics research, but can provide valuable project direction.

Toward Modeling Creative Processes for Algorithmic Painting

no code implementations3 May 2022 Aaron Hertzmann

This paper proposes a framework for computational modeling of artistic painting algorithms, inspired by human creative practices.

Neural Strokes: Stylized Line Drawing of 3D Shapes

1 code implementation ICCV 2021 Difan Liu, Matthew Fisher, Aaron Hertzmann, Evangelos Kalogerakis

We show that, in contrast to previous image-based methods, the use of a geometric representation of 3D shape and 2D strokes allows the model to transfer important aspects of shape and texture style while preserving contours.

Contact-Aware Retargeting of Skinned Motion

no code implementations ICCV 2021 Ruben Villegas, Duygu Ceylan, Aaron Hertzmann, Jimei Yang, Jun Saito

Self-contacts, such as when hands touch each other or the torso or the head, are important attributes of human body language and dynamics, yet existing methods do not model or preserve these contacts.

Motion Estimation motion retargeting

The Role of Edges in Line Drawing Perception

no code implementations22 Jan 2021 Aaron Hertzmann

It has often been conjectured that the effectiveness of line drawings can be explained by the similarity of edge images to line drawings.

Toward Quantifying Ambiguities in Artistic Images

no code implementations21 Aug 2020 Xi Wang, Zoya Bylinskii, Aaron Hertzmann, Robert Pepperell

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.

Predicting Visual Importance Across Graphic Design Types

no code implementations7 Aug 2020 Camilo Fosco, Vincent Casser, Amish Kumar Bedi, Peter O'Donovan, Aaron Hertzmann, Zoya Bylinskii

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 with a new dataset and applications.

Contact and Human Dynamics from Monocular Video

1 code implementation ECCV 2020 Davis Rempe, Leonidas J. Guibas, Aaron Hertzmann, Bryan Russell, Ruben Villegas, Jimei Yang

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 penetrating the ground and bodies leaning at extreme angles.

Human Dynamics Pose Estimation

GANSpace: Discovering Interpretable GAN Controls

2 code implementations NeurIPS 2020 Erik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, Sylvain Paris

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, lighting, and time of day.

Image Generation

Why Do Line Drawings Work? A Realism Hypothesis

no code implementations14 Feb 2020 Aaron Hertzmann

Why is it that we can recognize object identity and 3D shape from line drawings, even though they do not exist in the natural world?

Visual Indeterminacy in GAN Art

no code implementations10 Oct 2019 Aaron Hertzmann

This paper explores visual indeterminacy as a description for artwork created with Generative Adversarial Networks (GANs).

Image Generation

Im2Pencil: Controllable Pencil Illustration from Photographs

1 code implementation CVPR 2019 Yijun Li, Chen Fang, Aaron Hertzmann, Eli Shechtman, Ming-Hsuan Yang

We propose a high-quality photo-to-pencil translation method with fine-grained control over the drawing style.

Diversity Translation

Aesthetics of Neural Network Art

no code implementations13 Mar 2019 Aaron Hertzmann

This paper proposes a way to understand neural network artworks as juxtapositions of natural image cues.

Image Stylization

Visual Font Pairing

no code implementations19 Nov 2018 Shuhui Jiang, Zhaowen Wang, Aaron Hertzmann, Hailin Jin, Yun Fu

Third, font pairing is an asymmetric problem in that the roles played by header and body fonts are not interchangeable.

Metric Learning

Learning from Multi-domain Artistic Images for Arbitrary Style Transfer

1 code implementation25 May 2018 Zheng Xu, Michael Wilber, Chen Fang, Aaron Hertzmann, Hailin Jin

We propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs.

Style Transfer

Can Computers Create Art?

no code implementations13 Jan 2018 Aaron Hertzmann

It is then speculated about whether it could ever happen that AI systems could be credited with authorship of artwork.

BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography

no code implementations ICCV 2017 Michael J. Wilber, Chen Fang, Hailin Jin, Aaron Hertzmann, John Collomosse, Serge Belongie

Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of existing object classifiers, and for the study of visual domain adaptation.

Attribute Domain Adaptation

Preserving Color in Neural Artistic Style Transfer

7 code implementations19 Jun 2016 Leon A. Gatys, Matthias Bethge, Aaron Hertzmann, Eli Shechtman

This note presents an extension to the neural artistic style transfer algorithm (Gatys et al.).

Style Transfer

Exploratory Font Selection Using Crowdsourced Attributes

no code implementations ACM Transactions on Graphics 2014 Peter O'Donovan, Jānis Lībeks, Aseem Agarwala, Aaron Hertzmann

These tools are complementary; a user may search for "graceful" fonts, select a reasonable one, and then refine the results from a list of fonts similar to the selection.

Attribute Descriptive

Recognizing Image Style

1 code implementation15 Nov 2013 Sergey Karayev, Matthew Trentacoste, Helen Han, Aseem Agarwala, Trevor Darrell, Aaron Hertzmann, Holger Winnemoeller

The style of an image plays a significant role in how it is viewed, but style has received little attention in computer vision research.

Image Retrieval TAG

Efficient Optimization for Sparse Gaussian Process Regression

no code implementations NeurIPS 2013 Yanshuai Cao, Marcus A. Brubaker, David J. Fleet, Aaron Hertzmann

We propose an efficient optimization algorithm for selecting a subset of training data to induce sparsity for Gaussian process regression.


Cannot find the paper you are looking for? You can Submit a new open access paper.