Monocular depth using transformer, CNN, and uncertainty with URCDC-Depth
Monocular depth using transformer, CNN, and uncertainty with URCDC-Depth
URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation
arXiv paper abstract https://arxiv.org/abs/2302.08149
arXiv PDF paper https://arxiv.org/pdf/2302.08149.pdf
This work aims to estimate a high-quality depth map from a single RGB image.
... introduce an uncertainty rectified cross-distillation between Transformer and convolutional neural network (CNN) to learn a unified depth estimator.
... use the depth estimates derived from the Transformer branch and the CNN branch as pseudo labels to teach each other.
... model the pixel-wise depth uncertainty to rectify the loss weights of noisy depth labels.
To avoid the large performance gap induced by the strong Transformer branch deteriorating the cross-distillation, ... transfer the feature maps from Transformer to CNN and design coupling units to assist the weak CNN branch to utilize the transferred features.
... URCDC-Depth, exceeds previous state-of-the-art methods ... with no additional computational burden at inference time ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments