Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature.
We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution.
In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS).
We present You Only Cut Once (YOCO) for performing data augmentations.
We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown.
There are 2000 reference restored images and 6003 original underwater images in the unpaired training set.
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data.
Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world.