Show simple item record

dc.contributor.author
Maninis, Kevis-Kokitsi
dc.contributor.supervisor
Van Gool, Luc
dc.contributor.supervisor
Tombari, Federico
dc.contributor.supervisor
Kokkinos, Iasonas
dc.contributor.supervisor
Pont-Tuset, Jordi
dc.date.accessioned
2020-03-30T11:53:58Z
dc.date.available
2019-12-04T21:08:43Z
dc.date.available
2019-12-05T08:42:54Z
dc.date.available
2020-03-30T11:53:58Z
dc.date.issued
2019
dc.identifier.uri
http://hdl.handle.net/20.500.11850/382817
dc.identifier.doi
10.3929/ethz-b-000382817
dc.description.abstract
Scene understanding is one of the fastest growing areas in computer vision research. Such growth is mainly driven by the emergence of deep learning techniques that contributed to boosting performance on popular benchmarks for well-studied tasks, and to approaching tasks that have been very difficult to solve with traditional techniques. This dissertation examines how traditional low-level features such as boundaries and points help in tackling higher-level scene understanding tasks such as detection, segmentation, and 3D reconstruction. First, we propose a hierarchical grouping algorithm that uses deeply learned boundaries and their orientation. We examine how grouping from predicted boundaries can help object detection and semantic segmentation when plugged into the corresponding pipelines. Second, we use human-generated points for guided object segmentation. We show how to obtain segmented masks by using extreme points provided by humans, and how to speed up the time-consuming process of annotating for segmentation by using this technique. Third, we show how automatically detected keypoints help 3D re- construction in a complicated environment for robot-assisted retinal surgery. The task is to provide visual guidance during surgery by using two stereo cameras mounted on the surgical microscope. We propose a method for calibration, 3D registration, and 3D reconstruction from a single pipeline, by detecting specific robot keypoints, and by obtaining 3D to 2D correspondences just by moving the robot. Last, we examine the interplay of low-level and high-level tasks when trained jointly in a single neural network. We propose ways to overcome problems such as task interference and limited capacity as a result of jointly training for many different, unrelated tasks. We propose a universal network that can tackle all tasks, but only one task at a time. All in all, we show how to predict low-level features and how they contribute to different pipelines a) in combination with deep networks trained for scene understanding b) as human-generated input, c) in combination with 3D reconstruction, and d) by jointly training them with higher-level tasks.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
ETH Zurich
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Scene understanding
en_US
dc.subject
Segmentation
en_US
dc.subject
Multi-task learning
en_US
dc.subject
Boundary detection
en_US
dc.subject
3D reconstruction
en_US
dc.title
Exploiting Low-Level Features for Higher-Level Scene Understanding
en_US
dc.type
Doctoral Thesis
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2019-12-05
ethz.size
161 p.
en_US
ethz.code.ddc
DDC - DDC::0 - Computer science, information & general works::004 - Data processing, computer science
en_US
ethz.identifier.diss
26344
en_US
ethz.publication.place
Zurich
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::03514 - Van Gool, Luc / Van Gool, Luc
en_US
ethz.date.deposited
2019-12-04T21:08:51Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2019-12-05T08:43:26Z
ethz.rosetta.lastUpdated
2021-02-15T09:45:06Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Exploiting%20Low-Level%20Features%20for%20Higher-Level%20Scene%20Understanding&rft.date=2019&rft.au=Maninis,%20Kevis-Kokitsi&rft.genre=unknown&rft.btitle=Exploiting%20Low-Level%20Features%20for%20Higher-Level%20Scene%20Understanding
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record