K Crowson, S Biderman, D Kornis, D Stander… - … on Computer Vision, 2022 - Springer
Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models. We demonstrate a novel …
Denoising diffusion probabilistic models (DDPM) have shown remarkable performance in unconditional image generation. However, due to the stochasticity of the generative process …
We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as dense visual descriptors. We observe and empirically demonstrate that such features, when …
Y Pang, J Lin, T Qin, Z Chen - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations. I2I has drawn increasing attention and …
H Kim, Y Choi, J Kim, S Yoo… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the synthesized outputs, editing …
Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize …
We present an algorithm for re-rendering a person from a single image under arbitrary poses. Existing methods often have difficulties in hallucinating occluded contents photo …
This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high cost of obtaining hand-drawn sketch datasets, there is a lack of a …
The advent of large-scale training has produced a cornucopia of powerful visual recognition models. However, generative models, such as GANs, have traditionally been trained from …