Superpixel Cost Volume Excitation improves stereo matching accuracy by training cost-volume networks with a superpixel-pooled cross-entropy loss and superpixel-guided channel excitation.
In: Proceedings of the European Conference on Computer Vision (ECCV), pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Superpixel Cost Volume Excitation for Stereo Matching
Superpixel Cost Volume Excitation improves stereo matching accuracy by training cost-volume networks with a superpixel-pooled cross-entropy loss and superpixel-guided channel excitation.