Can I read Deep GrabCut for Object Selection on EtoBox?

Deep GrabCut for Object Selection by Xu, Ning; Price, Brian; Cohen, Scott; Yang, Jimei; Huang, Thomas is a scholarly article available to read on EtoBox.

What is Deep GrabCut for Object Selection about?

Most previous bounding-box-based segmentation methods assume the bounding box tightly covers the object of interest. However it is common that a rectangle input could be too large or too small. In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map. A convolutional encoder-decoder network is trained end-to-end by concatenating images with these distance maps as inputs and predicting the object masks as outputs. Our approach gets accurate segmentation results given sloppy rectangles while being general for both interactive segmentation and instance segmentation. We show our network extends to curve-based input without retraining. We further apply our network to instance-level semantic segmentation and resolve any overlap using a conditional random field. Experiments on benchmark datasets demonstrate the effectiveness of the proposed approaches.

Author

Xu, Ning; Price, Brian; Cohen, Scott; Yang, Jimei; Huang, Thomas

Published

2017

Language

EN