Search Results for author:
Found 23 papers, 19 papers with code
Guiding a Diffusion Model with a Bad Version of Itself
The primary axes of interest in image-generating diffusion models are image quality, the amount of variation in the results, and how well the results align with a given condition, e. g., a class label or a text prompt.
Ranked #1 on
Image Generation
on ImageNet 512x512
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
We show that guidance is clearly harmful toward the beginning of the chain (high noise levels), largely unnecessary toward the end (low noise levels), and only beneficial in the middle.
Ranked #5 on
Image Generation
on ImageNet 512x512
Analyzing and Improving the Training Dynamics of Diffusion Models
Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets.
Ranked #15 on
Image Generation
on ImageNet 512x512
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models.
Ranked #18 on
Text-to-Image Generation
on MS COCO
Simulator-Based Self-Supervision for Learned 3D Tomography Reconstruction
We propose a deep learning method for 3D volumetric reconstruction in low-dose helical cone-beam computed tomography.
eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
Therefore, in contrast to existing works, we propose to train an ensemble of text-to-image diffusion models specialized for different synthesis stages.
Ranked #14 on
Text-to-Image Generation
on MS COCO
Disentangling Random and Cyclic Effects in Time-Lapse Sequences
We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal.
Elucidating the Design Space of Diffusion-Based Generative Models
We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices.
Alias-Free Generative Adversarial Networks
We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner.
Ranked #1 on
Image Generation
on FFHQ-U
Modular Primitives for High-Performance Differentiable Rendering
We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines.
Training Generative Adversarial Networks with Limited Data
We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5. 59 to 2. 42.
Ranked #1 on
Conditional Image Generation
on ArtBench-10 (32x32)
Analyzing and Improving the Image Quality of StyleGAN
Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
Ranked #1 on
Image Generation
on LSUN Car 256 x 256
Semi-supervised semantic segmentation needs strong, high-dimensional perturbations
Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems.
Semi-supervised semantic segmentation needs strong, varied perturbations
We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success.
Improved Precision and Recall Metric for Assessing Generative Models
The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research.
Ranked #4 on
Image Generation
on FFHQ
Improved Self-Supervised Deep Image Denoising
We describe techniques for training high-quality image denoising models that require only single instances of corrupted images as training data.
High-Quality Self-Supervised Deep Image Denoising
We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images.
A Style-Based Generator Architecture for Generative Adversarial Networks
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.
Ranked #1 on
Image Generation
on LSUN Bedroom
Noise2Noise: Learning Image Restoration without Clean Data
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption.
Progressive Growing of GANs for Improved Quality, Stability, and Variation
We describe a new training methodology for generative adversarial networks.
Ranked #4 on
Image Generation
on LSUN Horse 256 x 256
(Clean-FID (trainfull) metric)
Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion
Our deep neural network learns a mapping from input waveforms to the 3D vertex coordinates of a face model, and simultaneously discovers a compact, latent code that disambiguates the variations in facial expression that cannot be explained by the audio alone.
Temporal Ensembling for Semi-Supervised Learning
In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled.
Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks
We present a real-time deep learning framework for video-based facial performance capture -- the dense 3D tracking of an actor's face given a monocular video.
