Sorry, you need to enable JavaScript to visit this website.

CONTEXT-AWARE AUTOMATIC OCCLUSION REMOVAL

Primary tabs

Citation Author(s):
Kumara Kahatapitiya, Dumindu Tissera, Ranga Rodrigo
Submitted by:
Kumara Kahatapitiya
Last updated:
21 September 2019 - 12:17am
Document Type:
Poster
Document Year:
2019
Event:
Presenters Name:
Mr. Dumindu Tissera
Paper Code:
2011

Abstract 

Abstract: 

Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal. No work tries to address automatic occlusion detection and removal as a context-aware generic problem. In this paper, we present a novel methodology to identify objects that do not relate to the image context as occlusions and remove them, reconstructing the space occupied coherently. The proposed system detects occlusions by considering the relation between foreground and background object classes represented as vector embeddings, and removes them through inpainting. We test our system on COCO-Stuff dataset and conduct a user study to establish a baseline in context-aware automatic occlusion removal.

up
0 users have voted:

Dataset Files

CONTEXT-AWARE AUTOMATIC OCCLUSION REMOVAL

(202)