3D scene analysis through non-visual cues

Simple item page
dc.contributor.authorMonszpart, Aron
dc.date.accessioned2020-01-22T08:53:28Z
dc.date.available2020-01-22T08:53:28Z
dc.date.issued2019-10-06
dc.description.abstractThe wide applicability of scene analysis from as few viewpoints as possible attracts the attention of many scientific fields, ranging from augmented reality to autonomous driving and robotics. When approaching 3D problems in the wild, one has to admit, that the problems to solve are particularly challenging due to a monocular setup being severely under-constrained. One has to design algorithmic solutions that resourcefully take advantage of abundant prior knowledge, much alike the way human reasoning is performed. I propose the utilization of non-visual cues to interpret visual data. I investigate, how making non-restrictive assumptions about the scene, such as “obeys Newtonian physics” or “is made by or for humans” greatly improves the quality of information retrievable from the same type of data. I successfully reason about the hidden constraints that shaped the acquired scene to come up with abstractions that represent likely estimates about the unobservable or difficult to acquire parts of scenes. I hypothesize, that jointly reasoning about these hidden processes and the observed scene allows for more accurate inference and lays the way for prediction through understanding. Applications of the retrieved information range from image and video editing (e.g., visual effects) through robotic navigation to assisted living.en_US
dc.description.sponsorshipERC Starting Grant SmartGeometry (StG-2013-335373) ERC PoC Grant (SemanticCity) ERC Starting Grant realFlow (StG-2015-637014) Marie Curie CIG, ANR Mapstyle project (ANR-12-COORD-0025) EU project CR-PLAY (no 611089) www.cr-play.eu NSFC (No. 61402402) Royal Society Advanced Newton Fellowship UCL Impact Google Faculty Awards Google PhD Fellowship Adobeen_US
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/2632870
dc.language.isoen_USen_US
dc.publisherUniversity College Londonen_US
dc.subjectgraphicsen_US
dc.subjectcomputer graphicsen_US
dc.subjectcomputer visionen_US
dc.subjectscene analysisen_US
dc.subjectrgbden_US
dc.subjectvideo analysisen_US
dc.subjectoptimizationen_US
dc.subjectmachine learningen_US
dc.subjectocclusionen_US
dc.subjectphysicsen_US
dc.subjectacquisitionen_US
dc.title3D scene analysis through non-visual cuesen_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
MonszpartPhdThesis.pdf
Size:
234.37 MB
Format:
Adobe Portable Document Format
Description:
PhD thesis
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.79 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
2019