Sparse, Smart Contours to Represent and Edit Images
computer vision and pattern recognition, pp. 3511-3520, 2018.
We study the problem of reconstructing an image from information stored at contour locations. We show that high-quality reconstructions with high fidelity to the source image can be obtained from sparse input, e.g., comprising less than 6% of image pixels. This is a significant improvement over existing contour-based reconstruction method...More
PPT (Upload PPT)