computer-vision-4
Referring Image Matting (Prompt-based)
3260 papers • 126 benchmarks • 313 datasets
Prompt-based referring image matting, taking an image and a prompt word as the input.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in referring-image-matting-prompt-based-4
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find referring-image-matting-prompt-based-4 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
PaintSeg: Training-free Segmentation via Painting
B. Raj, Zicheng Liu, Yinpeng Chen, Jinglu Wang, Xiang Li, Chung-Ching Lin•Mon May 29 2023
An adversarial masked contrastive painting process, which creates a contrast between the original image and a painted image in which a masked area is painted using off-the-shelf generative models, providing a training-free solution suitable for unsupervised segmentation.
8