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.
Image Source: Real-Time High-Resolution Background Matting
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
To bridge the domain gap to real imagery with no labeling, we train another matting network guided by the first network and by a discriminator that judges the quality of composites.
Ranked #1 on Image Matting on Adobe Matting
For portrait matting without the green screen, existing works either require auxiliary inputs that are costly to obtain or use multiple models that are computationally expensive.
Ranked #1 on Image Matting on PHM-100
We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.
Specifically, we propose a novel Glance and Focus Matting network (GFM), which employs a shared encoder and two separate decoders to learn both tasks in a collaborative manner for end-to-end animal image matting.
Ranked #1 on Image Matting on AM-2K
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Ranked #1 on Scene Segmentation on SUN-RGBD
We show that existing upsampling operators can be unified with the notion of the index function.
Ranked #4 on Image Matting on Composition-1K
Inspired by affinity-based method and the successes of contextual attention in inpainting, we develop a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matting.