Stay Positive: Non-Negative Image Synthesis for Augmented Reality
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Stay Positive : Non-Negative Image Synthesis for Augmented Reality. / Luo, Katie; Yang, Guandao; Xian, Wenqi; Haraldsson, Harald; Hariharan, Bharath; Belongie, Serge.
In: IEEE Conference on Computer Vision and Pattern Recognition, 2021, p. 10045-10055.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Stay Positive
T2 - IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
AU - Luo, Katie
AU - Yang, Guandao
AU - Xian, Wenqi
AU - Haraldsson, Harald
AU - Hariharan, Bharath
AU - Belongie, Serge
PY - 2021
Y1 - 2021
N2 - In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image. Most image generation methods, however, are ill-suited to this problem setting, as they make the assumption that one can assign arbitrary color to each pixel. In fact, naive application of existing methods fails even in simple domains such as MNIST digits, since one cannot create darker pixels by adding light. We know, however, that the human visual system can be fooled by optical illusions involving certain spatial configurations of brightness and contrast. Our key insight is that one can leverage this behavior to produce high quality images with negligible artifacts. For example, we can create the illusion of darker patches by brightening surrounding pixels. We propose a novel optimization procedure to produce images that satisfy both semantic and non-negativity constraints. Our approach can incorporate existing state-of-the-art methods, and exhibits strong performance in a variety of tasks including image-to-image translation and style transfer.
AB - In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image. Most image generation methods, however, are ill-suited to this problem setting, as they make the assumption that one can assign arbitrary color to each pixel. In fact, naive application of existing methods fails even in simple domains such as MNIST digits, since one cannot create darker pixels by adding light. We know, however, that the human visual system can be fooled by optical illusions involving certain spatial configurations of brightness and contrast. Our key insight is that one can leverage this behavior to produce high quality images with negligible artifacts. For example, we can create the illusion of darker patches by brightening surrounding pixels. We propose a novel optimization procedure to produce images that satisfy both semantic and non-negativity constraints. Our approach can incorporate existing state-of-the-art methods, and exhibits strong performance in a variety of tasks including image-to-image translation and style transfer.
U2 - 10.1109/CVPR46437.2021.00992
DO - 10.1109/CVPR46437.2021.00992
M3 - Conference article
SP - 10045
EP - 10055
JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SN - 1063-6919
Y2 - 19 June 2021 through 25 June 2021
ER -
ID: 303680094