computer-vision-10

Referring Image Matting (Expression-based)

3260 papers • 126 benchmarks • 313 datasets

Expression-based referring image matting, taking an image and a flowery expression as the input.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in referring-image-matting-expression-based-10

Trend

Dataset

Best Model

Actions

RefMatte

Libraries

i

Use these libraries to find referring-image-matting-expression-based-10 models and implementations

Datasets

RefMatte

Subtasks

No subtasks available.

Most implemented papers

Image Segmentation Using Text and Image Prompts

Alexander S. Ecker, Timo Lüddecke•Fri Dec 17 2021

This work proposes a system that can generate image segmentations based on arbitrary prompts at test time, and builds upon the CLIP model as a backbone which it extends with a transformer-based decoder that enables dense prediction.

668

Content

0

Paper Graph

Referring Image Matting

Jing Zhang, Jizhizi Li, Dacheng Tao•Thu Jun 09 2022

A large-scale challenging dataset Ref Matte is established by designing a comprehensive image composition and expression generation engine to automatically produce high-quality images along with diverse text attributes based on public datasets and presents a novel baseline method CLIPMat for RIM, including a context-embedded prompt, a text-driven semantic pop-up, and a multi-level details extractor.

34 0

Paper Graph

Adding a benchmark result helps the community track progress.