With the increasing demand for intelligent services, the sixth-generation (6G) wireless
networks will shift from a traditional architecture that focuses solely on a high transmission …

Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

By decomposing the image formation process into a sequential application of denoising
autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image …

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) …

Traditional approaches for learning 3D object categories have been predominantly trained
and evaluated on synthetic datasets due to the unavailability of real 3D-annotated category …

Perceiving the similarity between images has been a long-standing and fundamental
problem underlying various visual generation tasks. Predominant approaches measure the …

Existing image restoration methods mostly leverage the posterior distribution of natural
images. However, they often assume known degradation and also require supervised …

This paper explores a better prediction target for BERT pre-training of vision transformers.
We observe that current prediction targets disagree with human perception judgment. This …

Designed to learn long-range interactions on sequential data, transformers continue to show
state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no …

In image-to-image translation, each patch in the output should reflect the content of the
corresponding patch in the input, independent of domain. We propose a straightforward …