Neural scene representations for learning-based view synthesis
Thesis event information
Date and time of the thesis defence
Place of the thesis defence
L10, Linnanmaa campus
Topic of the dissertation
Neural scene representations for learning-based view synthesis
Doctoral candidate
Phong Nguyen
Faculty and unit
University of Oulu Graduate School, Faculty of Information Technology and Electrical Engineering, Center for Machine Vision and Signal Analysis (CMVS)
Subject of study
3D Computer Vision, Deep Learning
Opponent
Professor Serge Belongie, University of Copenhagen
Custos
Professor Janne Heikkilä, University of Oulu
Generating new views from a collections of images
This thesis introduces learning-based novel view synthesis approaches using different neural scene representations. Traditional representations, such as voxels or point clouds, are often computationally expensive and challenging to work with. Neural scene representations, on the other hand, can be more compact and efficient, allowing faster processing and better performance. Additionally, neural scene representations can be learned end-to-end from data, enabling them to be adapted to specific tasks and domains.
Last updated: 23.1.2024