An additive SSIM loss, with weights selected on the KITTI test split, yields small depth-error improvements over the multiplicative SSIM baseline in unsupervised monocular depth estimation.
In: NeurIPS (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation
An additive SSIM loss, with weights selected on the KITTI test split, yields small depth-error improvements over the multiplicative SSIM baseline in unsupervised monocular depth estimation.