Files in this item

FilesDescriptionFormat

application/pdf

application/pdfISSARANON-THESIS-2019.pdf (8MB)Restricted Access
(no description provided)PDF

Description

Title:Monocular depth prediction with object removal from single image
Author(s):Issaranon, Theerasit
Advisor(s):Forsyth, David
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Single-Image Depth Prediction
Object Removal
Occluded Vision
Abstract:We describe a method that predicts, from a single RGB image, a depth map that describes the scene when a masked object is removed – we call this “counterfactual depth” that models hidden scene geometry together with the observations. Our method works for the same reason that scene completion works: the spatial structure of objects is simple. But we offer a much higher resolution representation of space than current scene completion methods, as we operate at pixel-level precision and do not rely on a voxel representation. We can remove objects arbitrarily with an instructed object mask. Furthermore, we do not require RGBD inputs. Our method uses a standard encoder-decoder architecture, with a decoder modified to accept an object mask. We systematically construct a small evaluation dataset that we have collected. Using this dataset, we show that our depth predictions for masked objects are better than other baselines in the real scene. Given unmasked images, our approach performs comparatively well as a regular scene depth predictor.
Issue Date:2019-07-12
Type:Text
URI:http://hdl.handle.net/2142/105848
Rights Information:Copyright 2019 Theerasit Issaranon
Date Available in IDEALS:2019-11-26
Date Deposited:2019-08


This item appears in the following Collection(s)

Item Statistics