computer-vision-4
Point-interactive Image Colorization
3260 papers • 126 benchmarks • 313 datasets
Point-interactive colorization is a task of colorizing images given user-guided clicks containing colors (a.k.a color hints). Unlike unconditional image colorization, which is an underdetermined problem by nature, point-interactive colorization aims to generate images containing specific colors given by the user. Point-interactive colorization is evaluated by providing simulated user hints from the groundtruth color image. Following the iColoriT protocol, user hints have a size of 2x2 pixels and color is given as the average color within the 2x2 pixels.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in point-interactive-image-colorization-4
Trend
Dataset
Best Model
Actions
Oxford 102 Flowers
Oxford 102 Flowers
CUB-200-2011
CUB-200-2011
ImageNet ctest10k
Libraries
iUse these libraries to find point-interactive-image-colorization-4 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Real-time user-guided image colorization with learned deep priors
Richard Zhang, Phillip Isola, Alexei A. Efros, Tianhe Yu, Jun-Yan Zhu, Angela S. Lin, Xinyang Geng•Sun May 07 2017
This work proposes a deep learning approach for user-guided image colorization, which directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network.
618