Search Results for author:
Found 21 papers, 15 papers with code
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.
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 #1 on
Image Generation
on ImageNet 512x512
Generative Novel View Synthesis with 3D-Aware Diffusion Models
We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image.
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.
Generating Long Videos of Dynamic Scenes
Existing video generation methods often fail to produce new content as a function of time while maintaining consistencies expected in real environments, such as plausible dynamics and object persistence.
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.
The Role of ImageNet Classes in Fréchet Inception Distance
Fr\'echet Inception Distance (FID) is the primary metric for ranking models in data-driven generative modeling.
What You Can Learn by Staring at a Blank Wall
We present a passive non-line-of-sight method that infers the number of people or activity of a person from the observation of a blank wall in an unknown room.
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
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)
Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization
We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region.
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
A Dataset of Multi-Illumination Images in the Wild
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation.
Flexible SVBRDF Capture with a Multi-Image Deep Network
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph.
Graphics I.3
Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
Unfortunately, the commonly used additive white noise (AWGN) models do not accurately reproduce the noise and the degradation encountered on these inputs.
Single-Image SVBRDF Capture with a Rendering-Aware Deep Network
Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures.
Graphics I.3
Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks
We propose a neural approach for fusing an arbitrary-length burst of photographs suffering from severe camera shake and noise into a sharp and noise-free image.
Differentiable Monte Carlo Ray Tracing through Edge Sampling
We introduce a general-purpose differentiable ray tracer, which, to our knowledge, is the first comprehensive solution that is able to compute derivatives of scalar functions over a rendered image with respect to arbitrary scene parameters such as camera pose, scene geometry, materials, and lighting parameters.
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.
