Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Webster, Ryan"'
Autor:
Webster, Ryan
Recently, Carlini et al. demonstrated the widely used model Stable Diffusion can regurgitate real training samples, which is troublesome from a copyright perspective. In this work, we provide an efficient extraction attack on par with the recent atta
Externí odkaz:
http://arxiv.org/abs/2305.08694
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
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
Autor:
Wagner, Kevin, Stone, Jordan, Dong, Ruobing, Ertel, Steve, Apai, Daniel, Doelman, David, Bohn, Alexander, Najita, Joan, Brittain, Sean, Kenworthy, Matthew, Keppler, Miriam, Webster, Ryan, Mailhot, Emily, Snik, Frans
Scattered light imaging has revealed nearly a dozen circumstellar disks around young Herbig Ae/Be stars$-$enabling studies of structures in the upper disk layers as potential signs of on-going planet formation. We present the first images of the disk
Externí odkaz:
http://arxiv.org/abs/2004.06157
Autor:
Jones, Terry Jay, Williams, Liliya L. R., Ertel, Steve, Hinz, Philip M., Vaz, Amali, Walsh, Shane, Webster, Ryan
We report near simultaneous imaging using LMIRCam on the LBTI of the quadruply imaged lensed quasar HS 0810+2554 at wavelengths of 2.16, 3.7 and $4.78~\mu$m with a Full Width Half Max (FWHM) spatial resolution of $0^{\prime\prime}\!\!.13$, $0^{\prime
Externí odkaz:
http://arxiv.org/abs/1910.10561
Autor:
Wagner, Kevin, Stone, Jordan M., Spalding, Eckhart, Apai, Daniel, Dong, Ruobing, Ertel, Steve, Leisenring, Jarron, Webster, Ryan
Theoretical studies suggest that a giant planet around the young star MWC 758 could be responsible for driving the spiral features in its circumstellar disk. Here, we present a deep imaging campaign with the Large Binocular Telescope with the primary
Externí odkaz:
http://arxiv.org/abs/1907.06655
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
State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors,
Externí odkaz:
http://arxiv.org/abs/1901.03396
Autor:
Webster, Ryan
In this work, we present a non-parametric texture synthesis algorithm capable of producing plausible images without copying large tiles of the exemplar. We focus on a simple synthesis algorithm, where we explore two patch match heuristics; the well k
Externí odkaz:
http://arxiv.org/abs/1801.04619