Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Rabin, Julien"'
With the recent success of generative models in image and text, the evaluation of generative models has gained a lot of attention. Whereas most generative models are compared in terms of scalar values such as Frechet Inception Distance (FID) or Incep
Externí odkaz:
http://arxiv.org/abs/2405.01611
Publikováno v:
2023 IEEE International Conference on Image Processing (ICIP), Oct 2023, Kuala Lumpur, Malaysia. pp.1790-1794
This paper presents LatentPatch, a new method for generating realistic images from a small dataset of only a few images. We use a lightweight model with only a few thousand parameters. Unlike traditional few-shot generation methods that finetune pre-
Externí odkaz:
http://arxiv.org/abs/2401.16830
Generative models, such as DALL-E, Midjourney, and Stable Diffusion, have societal implications that extend beyond the field of computer science. These models require large image databases like LAION-2B, which contain two billion images. At this scal
Externí odkaz:
http://arxiv.org/abs/2303.12733
Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website {\small \url{ http://thispersondoesnotexist.com}}, taunts users with GAN generated images that
Externí odkaz:
http://arxiv.org/abs/2107.06018
This paper is devoted to signal processing on point-clouds by means of neural networks. Nowadays, state-of-the-art in image processing and computer vision is mostly based on training deep convolutional neural networks on large datasets. While it is a
Externí odkaz:
http://arxiv.org/abs/2103.16337
Publikováno v:
Transactions on Machine Learning Research (2023)
The use of optimal transport cost for learning generative models has become popular with Wasserstein Generative Adversarial Networks (WGAN). Training of WGAN relies on a theoretical background: the calculation of the gradient of the optimal transport
Externí odkaz:
http://arxiv.org/abs/2102.05542
The recent advent of powerful generative models has triggered the renewed development of quantitative measures to assess the proximity of two probability distributions. As the scalar Frechet inception distance remains popular, several methods have ex
Externí odkaz:
http://arxiv.org/abs/2006.11809
Publikováno v:
Journal of Mathematical Imaging and Vision, Volume 65, pages 4-28, (2023)
We propose GOTEX, a general framework for texture synthesis by optimization that constrains the statistical distribution of local features. While our model encompasses several existing texture models, we focus on the case where the comparison between
Externí odkaz:
http://arxiv.org/abs/2007.03408
This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high quality 3D data at interactive rates. Based on a few example images of textures, a generative n
Externí odkaz:
http://arxiv.org/abs/2001.04528
Publikováno v:
PMLR 97:5799-5808, 2019
In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than providing a scalar for generative quality, PR curves distinguish mode-collapse (poor recall) an
Externí odkaz:
http://arxiv.org/abs/1905.05441