A deep congealing method using a fused spatial transformer network and a penalised auto-encoder aligns image ensembles of up to one million images with improved robustness over prior baselines.
DeSTNet: Densely fused spatial transformer networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Jointly Aligning Millions of Images with Deep Penalised Reconstruction Congealing
A deep congealing method using a fused spatial transformer network and a penalised auto-encoder aligns image ensembles of up to one million images with improved robustness over prior baselines.