|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.
SOTA for Image Matting on Adobe Matting
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.
Our method employs two encoder networks to extract essential information for matting.
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.
SOTA for Scene Segmentation on SUN-RGBD
We show that existing upsampling operators can be unified with the notion of the index function.
#2 best model for Image Matting on Composition-1K
In order to achieve automatic compositing in natural scenes, we propose 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.