Zobrazeno 1 - 10
of 1 395
pro vyhledávání: '"Park Taesung"'
Autor:
Yin, Tianwei, Gharbi, Michaël, Park, Taesung, Zhang, Richard, Shechtman, Eli, Durand, Fredo, Freeman, William T.
Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without enforcing a one-
Externí odkaz:
http://arxiv.org/abs/2405.14867
Autor:
Kang, Minguk, Zhang, Richard, Barnes, Connelly, Paris, Sylvain, Kwak, Suha, Park, Jaesik, Shechtman, Eli, Zhu, Jun-Yan, Park, Taesung
We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality. Our approach interprets diffusion distillation as a paired image
Externí odkaz:
http://arxiv.org/abs/2405.05967
Autor:
Mu, Jiteng, Gharbi, Michaël, Zhang, Richard, Shechtman, Eli, Vasconcelos, Nuno, Wang, Xiaolong, Park, Taesung
Diffusion models have made significant advances in text-guided synthesis tasks. However, editing user-provided images remains challenging, as the high dimensional noise input space of diffusion models is not naturally suited for image inversion or sp
Externí odkaz:
http://arxiv.org/abs/2404.16029
Autor:
Xu, Yiran, Park, Taesung, Zhang, Richard, Zhou, Yang, Shechtman, Eli, Liu, Feng, Huang, Jia-Bin, Liu, Difan
Video super-resolution (VSR) approaches have shown impressive temporal consistency in upsampled videos. However, these approaches tend to generate blurrier results than their image counterparts as they are limited in their generative capability. This
Externí odkaz:
http://arxiv.org/abs/2404.12388
Autor:
Nitzan, Yotam, Wu, Zongze, Zhang, Richard, Shechtman, Eli, Cohen-Or, Daniel, Park, Taesung, Gharbi, Michaël
We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image updates efficiently. Our approach targets interactive image editing applications in which, starting from a blank canvas or an image, a user specifies a sequence o
Externí odkaz:
http://arxiv.org/abs/2404.12382
Model customization introduces new concepts to existing text-to-image models, enabling the generation of these new concepts/objects in novel contexts. However, such methods lack accurate camera view control with respect to the new object, and users m
Externí odkaz:
http://arxiv.org/abs/2404.12333
In this work, we address two limitations of existing conditional diffusion models: their slow inference speed due to the iterative denoising process and their reliance on paired data for model fine-tuning. To tackle these issues, we introduce a gener
Externí odkaz:
http://arxiv.org/abs/2403.12036
Recently, MBConv blocks, initially designed for efficiency in resource-limited settings and later adapted for cutting-edge image classification performances, have demonstrated significant potential in image classification tasks. Despite their success
Externí odkaz:
http://arxiv.org/abs/2402.04618
A jump cut offers an abrupt, sometimes unwanted change in the viewing experience. We present a novel framework for smoothing these jump cuts, in the context of talking head videos. We leverage the appearance of the subject from the other source frame
Externí odkaz:
http://arxiv.org/abs/2401.04718
Autor:
Yin, Tianwei, Gharbi, Michaël, Zhang, Richard, Shechtman, Eli, Durand, Fredo, Freeman, William T., Park, Taesung
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
Diffusion models generate high-quality images but require dozens of forward passes. We introduce Distribution Matching Distillation (DMD), a procedure to transform a diffusion model into a one-step image generator with minimal impact on image quality
Externí odkaz:
http://arxiv.org/abs/2311.18828