We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3
adapts denoising diffusion probabilistic models (Ho et al. 2020),(Sohl-Dickstein et al. 2015) …

Score-based generative models (SGMs) synthesize new data samples from Gaussian white
noise by running a time-reversed Stochastic Differential Equation (SDE) whose drift …

Video understanding calls for a model to learn the characteristic interplay between static
scene content and its dynamics: Given an image, the model must be able to predict a future …

Invertible image decolorization is a useful color compression technique to reduce the cost in
multimedia systems. Invertible decolorization aims to synthesize faithful grayscales from …

We propose Multiscale Flow, a generative Normalizing Flow that creates samples and
models the field-level likelihood of two-dimensional cosmological data such as weak …

With the continuous development of imaging technology and the gradual expansion of the
amount of image data, how to achieve high compression efficiency of high-resolution …

Learning neural networks using only few available information is an important ongoing
research topic with tremendous potential for applications. In this paper, we introduce a …

In recent years, the neural radiance field (NeRF) model has gained popularity due to its
ability to recover complex 3D scenes. Following its success, many approaches proposed …