Skip to main navigation
Skip to search
Skip to main content
TU Delft Research Portal Home
Help & FAQ
Home
Research units
Researchers
Research output
Datasets
Projects
Equipment
Press/Media
Prizes
Activities
Search by expertise, name or affiliation
Data-efficient learning of geometric structures from single-view images
Y. Lin
Pattern Recognition and Bioinformatics
Research output
:
Thesis
›
Dissertation (TU Delft)
59
Downloads (Pure)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Data-efficient learning of geometric structures from single-view images'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Computer Science
Autonomous Agent
33%
Deep Learning
33%
Deep Neural Network
33%
Design
33%
Hough Transforms
66%
lane detection
33%
Massive Amount
33%
Model
100%
Neural Network
100%
Parameter Space
33%
Parsing
33%
Point Detection
33%
Real World
66%
Representation Learning
33%
Scene Understanding
33%
Training Data
66%
Training Sample
33%
Unlabeled Data
33%
INIS
availability
10%
cities
10%
comparative evaluations
10%
data
100%
datasets
30%
design
10%
detection
20%
geometry
100%
hands
20%
humans
10%
images
100%
information
10%
junctions
10%
learning
100%
mapping
10%
mirrors
20%
neural networks
40%
performance
50%
shape
20%
space
20%
spheres
10%
symmetry
20%
transformers
30%
tuning
10%
variations
10%
Keyphrases
3d Mirror Symmetry
25%
Artificial World
25%
Automatic Understanding
25%
Coherent Pattern
25%
Edge Feature
25%
Gaussian Sphere
25%
Line Junction
25%
Orthogonal Vanishing Points
25%
Parallel Transformer
25%
Polygon Representation
25%
Repetitive Structures
25%
Sphere Mappings
25%
Spherical Deconvolution
25%
Vanishing Point Detection
25%
Visual Scene Understanding
25%
Visual Space
25%
Material Science
Mechanical Strength
100%
Mathematics
Vanishing Point
66%