Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Using NeRF- and Mesh-Based Methods to Improve Visualisation of Point Clouds

Ylvén, Vilma LU and Montelin, Oscar LU (2024) In Master’s Theses in Mathematical Sciences FMAM05 20232
Mathematics (Faculty of Engineering)
Abstract
In recent years, the field of generating synthetic images from novel view points has seen some major improvements. Most importantly with the publication of Neural Radiance Fields allowing for extremely detailed and accurate 3D novel views. Usage of LiDAR products to collect actual depth data has also seen an increase as it is immensely useful for achieving high resolution 3D mapping of a space. However, these point clouds can be hard to read as they give a discrete sample of surfaces and lack colour and texture. In this thesis we explore various ways of improving visualisation and human understanding of scenes and objects generated from a stationary camera-LiDAR pair. We do this by first isolating individual rigid moving objects ina scene... (More)
In recent years, the field of generating synthetic images from novel view points has seen some major improvements. Most importantly with the publication of Neural Radiance Fields allowing for extremely detailed and accurate 3D novel views. Usage of LiDAR products to collect actual depth data has also seen an increase as it is immensely useful for achieving high resolution 3D mapping of a space. However, these point clouds can be hard to read as they give a discrete sample of surfaces and lack colour and texture. In this thesis we explore various ways of improving visualisation and human understanding of scenes and objects generated from a stationary camera-LiDAR pair. We do this by first isolating individual rigid moving objects ina scene and constructing denser point clouds of these objects by projecting them on the camera video and aggregating over time. By utilising the novel view synthesis method Point-NeRF, we also improve visualisation of these dense point clouds further. This is done by training a point-based neural network on the aggregated point clouds and the corresponding video frames. Lastly two methods for surface reconstruction of objects and the backgrounds are tested. With this we achieve accurate and understandable renders of a variety of vehicles. We believe that with a well calibrated camera this method shows significant promise for reconstructing scenes in 3D in post-processing well. (Less)
Please use this url to cite or link to this publication:
author
Ylvén, Vilma LU and Montelin, Oscar LU
supervisor
organization
course
FMAM05 20232
year
type
H2 - Master's Degree (Two Years)
subject
publication/series
Master’s Theses in Mathematical Sciences
report number
LUTFMA-3525-2024
ISSN
1404-6342
other publication id
2024:E6
language
English
id
9146759
date added to LUP
2024-02-05 13:04:20
date last changed
2024-02-05 13:04:20
@misc{9146759,
  abstract     = {{In recent years, the field of generating synthetic images from novel view points has seen some major improvements. Most importantly with the publication of Neural Radiance Fields allowing for extremely detailed and accurate 3D novel views. Usage of LiDAR products to collect actual depth data has also seen an increase as it is immensely useful for achieving high resolution 3D mapping of a space. However, these point clouds can be hard to read as they give a discrete sample of surfaces and lack colour and texture. In this thesis we explore various ways of improving visualisation and human understanding of scenes and objects generated from a stationary camera-LiDAR pair. We do this by first isolating individual rigid moving objects ina scene and constructing denser point clouds of these objects by projecting them on the camera video and aggregating over time. By utilising the novel view synthesis method Point-NeRF, we also improve visualisation of these dense point clouds further. This is done by training a point-based neural network on the aggregated point clouds and the corresponding video frames. Lastly two methods for surface reconstruction of objects and the backgrounds are tested. With this we achieve accurate and understandable renders of a variety of vehicles. We believe that with a well calibrated camera this method shows significant promise for reconstructing scenes in 3D in post-processing well.}},
  author       = {{Ylvén, Vilma and Montelin, Oscar}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master’s Theses in Mathematical Sciences}},
  title        = {{Using NeRF- and Mesh-Based Methods to Improve Visualisation of Point Clouds}},
  year         = {{2024}},
}