A Holistic Approach for Data-Driven Object Cutout

A cluttered scene with four chairs (a); an aggregated P-map visualizing object detection (b); local P-maps inside proposed rectangles (c) ; cutouts produced with the aid of our local P-maps (d) ; cutouts produced using GrabCut, for the same rectangles (e) .

Object cutout is a fundamental operation for image editing and manipulation, yet it is extremely challenging to automate it in real-world images, which typically contain considerable background clutter. In contrast to existing cutout methods, which are based mainly on low-level image analysis, we propose a more \emph{holistic} approach, which considers the entire shape of the object of interest by leveraging higher-level image analysis and learnt global shape priors. Specifically, we leverage a deep neural network (DNN) trained for objects of a particular class (chairs) for realizing this mechanism. Given a rectangular image region, the DNN outputs a probability map (P-map) that indicates for each pixel inside the rectangle how likely it is to be contained inside an object from the class of interest. We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask. This amounts to an automatic end-to-end pipeline for catergory-specific object cutout. We evaluate our approach on segmentation benchmark datasets, and show that it significantly outperforms the state-of-the-art on them.

We would first like to thank all the reviewers for their valuable comments and suggestions. This work is supported in part by grants from National 973 Program (2015CB352501), NSFC-ISF(61561146397), Shenzhen Knowledge innovation program for basic research (JCYJ20150402105524053)

@Article{Cutout,
Title = {A Holistic Approach for Data-Driven Object Cutout},
Author = {Huayong Xu and Yangyan Li and Wenzheng Chen and Dani Lischinski and Daniel Cohen-Or and Baoquan Chen},
Journal = {Proceedings of ACCV 2016},
Year = {2016},
Number = {to appear},
Pages = {to appear},
Volume = {to appear}
}