Point-interactive Image Colorization
4 papers with code • 3 benchmarks • 3 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.
Benchmarks
These leaderboards are used to track progress in Point-interactive Image Colorization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
CUB-200-2011
Oxford 102 Flower
ImageNet ctest10k
Most implemented papers
Real-Time User-Guided Image Colorization with Learned Deep Priors
junyanz/interactive-deep-colorization
•
•
The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network (CNN).
Instance-aware Image Colorization
ericsujw/InstColorization
•
•
CVPR 2020
Previous methods leverage the deep neural network to map input grayscale images to plausible color outputs directly.
Side Window Filtering
wang-kangkang/SideWindowFilter-pytorch
•
•
CVPR 2019
In addition to image filtering, we further show that the SWF principle can be extended to other applications involving the use of a local window.
iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer
pmh9960/iColoriT
•
•
It is essential for point-interactive colorization methods to appropriately propagate user-provided colors (i. e., user hints) in the entire image to obtain a reasonably colorized image with minimal user effort.
