TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Image Matting

Image Matting

30 benchmarks225 papers

Image Matting is the process of accurately estimating the foreground object in images and videos. It is a very important technique in image and video editing applications, particularly in film production for creating visual effects. In case of image segmentation, we segment the image into foreground and background by labeling the pixels. Image segmentation generates a binary image, in which a pixel either belongs to foreground or background. However, Image Matting is different from the image segmentation, wherein some pixels may belong to foreground as well as background, such pixels are called partial or mixed pixels. In order to fully separate the foreground from the background in an image, accurate estimation of the alpha values for partial or mixed pixels is necessary.

<span class="description-source">Source: Automatic Trimap Generation for Image Matting </span>

<span class="description-source">Image Source: Real-Time High-Resolution Background Matting</span>

Benchmarks

Image Matting on Composition-1K

MSEConnGradSAD

Image Matting on AM-2K

SADMSEMAD

Image Matting on P3M-10k

SADMSEMAD

Image Matting on AIM-500

SADMSEMADConn.Grad.

Image Matting on Adobe Matting

MSESAD

Image Matting on Distinctions-646

SADMSEGradConnTrimap

Image Matting on Semantic Image Matting Dataset

ConnGradMSE(10^3)SAD

Image Matting on AMD

MADMSE

Image Matting on PPM-100

MADMSE