Outdoor Image Understanding from Multiple Vision Modalities

Fecisti nos ad te, Domine,
et inquietum est cor nostrum donec requiescat in te.
Augustine of Hippo

Abstract

The thesis investigates various computer vision modalities, which, taken from the broad definitions, include both sensory data as well as subsequent interpretation such as RGB, depth, intrinsic images, semantic maps, surface normals, optical flow, and point clouds. Specifically, the thesis focuses on the research question how various computer vision modalities can be exploited and combined. The question is tackled from multiple perspectives, starting with decomposing a primary modality, followed by the study of modality complement and combination. The subsequent chapters explore multimodality from a generative perspective, how a modality benefits generation of the others, and concludes with the construction of a multimodal synthetic dataset.

Doctoral Committee

Chairman: Prof. Peter van Emde-Boas, Universiteit van Amsterdam

Promoters:

• Prof. Theo Gevers, Universiteit van Amsterdam
• Dr. Thomas Mensink, Google Research

Committee Members:

• Prof. Robert Fisher, University of Edinburgh
• Prof. Sébastien Lefèvre, Université Bretagne-Sud
• Prof. Cees Snoek, Universiteit van Amsterdam
• Dr. Arnoud Visser, Universiteit van Amsterdam
• Dr. Sezer Karaoğlu, Universiteit van Amsterdam

Doctoral Thesis

• Official record in UvA Library | PDF
• Mirror on Offpage (pw: 2ez6zz) | Flipbook
• Thesis Template

PhD defense ceremony

• 18/05/2021 at 12PM, in the Agnietekapel, University of Amsterdam

• Paranymphs: Ngô Lê Minh, Anıl Sırrı Başlamışlı

Citation

If you find the material useful please consider citing our work

@phdthesis{le21thesis,
 author = "L{\^{e}}, Ho{\`{a}}ng{-}{\^{A}}n",
 title = {{Outdoor Image Understanding from Multiple Vision Modalities}},
 school   = {University of Amsterdam},
 year = {2021},
}