24 citations · 86 across the 21 of their papers we have counts for
22 papers · 1 filter
The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric
Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann +4
Human visual similarity judgments are context-dependent. For example, two images may be similar in shape but distinct in color. Existing perceptual similarity metrics, however, col…
Fast Data Attribution for Text-to-Image Models
Sheng-Yu Wang, Aaron Hertzmann, Alexei A Efros +2
Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considera…
Identifying Prompted Artist Names from Generated Images
Grace Su, Sheng-Yu Wang, Aaron Hertzmann +3
A common and controversial use of text-to-image models is to generate pictures by explicitly naming artists, such as "in the style of Greg Rutkowski". We introduce a benchmark for…
What Makes for a Good Stereoscopic Image?
Netanel Y. Tamir, Shir Amir, Ranel Itzhaky +8
With rapid advancements in virtual reality (VR) headsets, effectively measuring stereoscopic quality of experience (SQoE) has become essential for delivering immersive and comforta…
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
Sheng-Yu Wang, Aaron Hertzmann, Alexei A. Efros +2
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. Influence is defined such that, for a gi…
Evaluating Data Attribution for Text-to-Image Models
Sheng-Yu Wang, Alexei A. Efros, Jun-Yan Zhu +1
While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such mode…
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
Stephanie Fu, Netanel Tamir, Shobhita Sundaram +4
Current perceptual similarity metrics operate at the level of pixels and patches. These metrics compare images in terms of their low-level colors and textures, but fail to capture…
Ablating Concepts in Text-to-Image Diffusion Models
Nupur Kumari, Bingliang Zhang, Sheng-Yu Wang +3
Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous amount…
Scaling up GANs for Text-to-Image Synthesis
Minguk Kang, Jun-Yan Zhu, Richard Zhang +4
The recent success of text-to-image synthesis has taken the world by storm and captured the general public's imagination. From a technical standpoint, it also marked a drastic chan…
Zero-shot Image-to-Image Translation
Gaurav Parmar, Krishna Kumar Singh, Richard Zhang +3
Large-scale text-to-image generative models have shown their remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply th…
Domain Expansion of Image Generators
Yotam Nitzan, Michaël Gharbi, Richard Zhang +4
Can one inject new concepts into an already trained generative model, while respecting its existing structure and knowledge? We propose a new task - domain expansion - to address t…
Multi-Concept Customization of Text-to-Image Diffusion
Nupur Kumari, Bingliang Zhang, Richard Zhang +2
While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for exa…
Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
Gaurav Parmar, Yijun Li, Jingwan Lu +3
Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categori…
BlobGAN: Spatially Disentangled Scene Representations
Dave Epstein, Taesung Park, Richard Zhang +2
We propose an unsupervised, mid-level representation for a generative model of scenes. The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes…
Any-resolution Training for High-resolution Image Synthesis
Lucy Chai, Michael Gharbi, Eli Shechtman +2
Generative models operate at fixed resolution, even though natural images come in a variety of sizes. As high-resolution details are downsampled away and low-resolution images are…
Ensembling Off-the-shelf Models for GAN Training
Nupur Kumari, Richard Zhang, Eli Shechtman +1
The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from s…
GAN-Supervised Dense Visual Alignment
William Peebles, Jun-Yan Zhu, Richard Zhang +3
We propose GAN-Supervised Learning, a framework for learning discriminative models and their GAN-generated training data jointly end-to-end. We apply our framework to the dense vis…
Contrastive Feature Loss for Image Prediction
Alex Andonian, Taesung Park, Bryan Russell +3
Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result. Yet, this basic functionality remains an open problem. A popular…
Editing Conditional Radiance Fields
Steven Liu, Xiuming Zhang, Zhoutong Zhang +3
A neural radiance field (NeRF) is a scene model supporting high-quality view synthesis, optimized per scene. In this paper, we explore enabling user editing of a category-level NeR…
Ensembling with Deep Generative Views
Lucy Chai, Jun-Yan Zhu, Eli Shechtman +2
Recent generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose, simply by learning from unlabeled image col…
Few-shot Image Generation via Cross-domain Correspondence
Utkarsh Ojha, Yijun Li, Jingwan Lu +4
Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large sourc…
On Aliased Resizing and Surprising Subtleties in GAN Evaluation
Gaurav Parmar, Richard Zhang, Jun-Yan Zhu
Metrics for evaluating generative models aim to measure the discrepancy between real and generated images. The often-used Frechet Inception Distance (FID) metric, for example, extr…