Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Chai, Lucy"'
Autor:
Sundaram, Shobhita, Fu, Stephanie, Muttenthaler, Lukas, Tamir, Netanel Y., Chai, Lucy, Kornblith, Simon, Darrell, Trevor, Isola, Phillip
Humans judge perceptual similarity according to diverse visual attributes, including scene layout, subject location, and camera pose. Existing vision models understand a wide range of semantic abstractions but improperly weigh these attributes and th
Externí odkaz:
http://arxiv.org/abs/2410.10817
Autor:
Chai, Lucy
Image synthesis has developed at an unprecedented pace over the past few years, giving us new abilities to create synthetic yet photorealistic content. Typically, unconditional synthesis takes in a tensor of random numbers as input and produces a ran
Externí odkaz:
https://hdl.handle.net/1721.1/152643
Autor:
Fu, Stephanie, Tamir, Netanel, Sundaram, Shobhita, Chai, Lucy, Zhang, Richard, Dekel, Tali, Isola, Phillip
Current perceptual similarity metrics operate at the level of pixels and patches. These metrics compare images in terms of their low-level colors and textures, but fail to capture mid-level similarities and differences in image layout, object pose, a
Externí odkaz:
http://arxiv.org/abs/2306.09344
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes, enabling arbitra
Externí odkaz:
http://arxiv.org/abs/2303.13515
Autor:
Ma, Jingwei, Chai, Lucy, Huh, Minyoung, Wang, Tongzhou, Lim, Ser-Nam, Isola, Phillip, Torralba, Antonio
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene. Totems bend and redirect light rays, thus providing multiple, albeit distorte
Externí odkaz:
http://arxiv.org/abs/2209.13032
Generative models operate at fixed resolution, even though natural images come in a variety of sizes. As high-resolution details are downsampled away and low-resolution images are discarded altogether, precious supervision is lost. We argue that ever
Externí odkaz:
http://arxiv.org/abs/2204.07156
Recent generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose, simply by learning from unlabeled image collections. Here, we investigate whether such views can be applied to re
Externí odkaz:
http://arxiv.org/abs/2104.14551
In recent years, Generative Adversarial Networks have become ubiquitous in both research and public perception, but how GANs convert an unstructured latent code to a high quality output is still an open question. In this work, we investigate regressi
Externí odkaz:
http://arxiv.org/abs/2103.10426
The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle artifacts in the
Externí odkaz:
http://arxiv.org/abs/2008.10588
An open secret in contemporary machine learning is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. This has been attributed to biased training data, which provide poor coverage over real world events.
Externí odkaz:
http://arxiv.org/abs/1907.07171