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 -