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 …
R Rombach, A Blattmann, D Lorenz… - Proceedings of the …, 2022 - openaccess.thecvf.com
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 …
F Zhan, J Zhang, Y Yu, R Wu… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …
P Esser, R Rombach, B Ommer - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
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 …