Denoising diffusion models are a powerful type of generative models used...
Separating an image into meaningful underlying components is a crucial f...
Diffusion models excel at text-to-image generation, especially in
subjec...
Video conferencing systems suffer from poor user experience when network...
We study the problem of extracting biometric information of individuals ...
Human perception reliably identifies movable and immovable parts of 3D
s...
We present a method to automatically compute correct gradients with resp...
Neural scene representations, both continuous and discrete, have recentl...
This paper presents an unpaired method for creating line drawings from
p...
We present a passive non-line-of-sight method that infers the number of
...
Inferring representations of 3D scenes from 2D observations is a fundame...
We present a whole-program optimization framework for the Taichi program...
Recognizing an object's category and pose lies at the heart of visual
un...
We introduce a new video synthesis task: synthesizing time lapse videos
...
We recover a video of the motion taking place in a hidden scene by obser...
Collections of images under a single, uncontrolled illumination have ena...
We study the problem of learning and optimizing through physical simulat...
We introduce visual deprojection: the task of recovering an image or vid...
Empowered by deep learning, recent methods for material capture can esti...
Image reconstruction techniques such as denoising often need to be appli...
Biomedical image segmentation is an important task in many medical
appli...
Texture, highlights, and shading are some of many visual cues that allow...
Winograd-based convolution has quickly gained traction as a preferred
ap...
Widely used in news, business, and educational media, infographics are
h...
We address the computational problem of novel human pose synthesis. Give...
Video motion magnification techniques allow us to see small motions
prev...
We introduce the problem of visual hashtag discovery for infographics:
e...
Knowing where people look and click on visual designs can provide clues ...
Performance is a critical challenge in mobile image processing. Given a
...
For many movement disorders, such as Parkinson's disease and ataxia, dis...
The inverse diffusion curve problem focuses on automatic creation of
dif...
How best to evaluate a saliency model's ability to predict where humans ...