computer-vision-5

Semantic Image Matting

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in semantic-image-matting-5

Trend

Dataset

Best Model

Actions

Semantic Image Matting Dataset

Libraries

i

Use these libraries to find semantic-image-matting-5 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Deep Image Matting

Thomas S. Huang, Scott D. Cohen, Brian L. Price, N. Xu•Thu Mar 09 2017

A novel deep learning based algorithm that can tackle image matting problems when an image has similar foreground and background colors or complicated textures and evaluation results demonstrate the superiority of this algorithm over previous methods.

493

Content

0

Paper Graph

Instance Segmentation Based Semantic Matting for Compositing Applications

Guanqing Hu, James J. Clark•Tue Apr 09 2019

This work proposes a fully automated method that integrates instance segmentation and image matting processes to generate high-quality semantic mattes that can be used for image editing task.

11 0

Paper Graph

Indices Matter: Learning to Index for Deep Image Matting

Chunhua Shen, Yutong Dai, Hao Lu, Songcen Xu•Thu Aug 01 2019

By viewing the indices as a function of the feature map, this work introduces the concept of 'learning to index', and presents a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the pooling and upsampling operators, without extra training supervision.

205 0

Paper Graph

Natural Image Matting via Guided Contextual Attention

Yaoyi Li, Hongtao Lu•Sun Jan 12 2020

This work develops a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matts and can mimic information flow of affinity-based methods and utilize rich features learned by deep neural networks simultaneously.

188 0

Paper Graph

Semantic Image Matting

Yu-Wing Tai, Chi-Keung Tang, Yanan Sun•Thu Apr 15 2021

This work considers and learns 20 classes of matting patterns, and proposes to extend the conventional trimap to semantic trimap, and adds a multi-class discriminator to regularize the alpha prediction at semantic level, and content-sensitive weights to balance different regularization losses.

105 0

Paper Graph

Adding a benchmark result helps the community track progress.