Learning-Deep-Learning

SMWA: On the Over-Smoothing Problem of CNN Based Disparity Estimation

November 2019

tl;dr: Use single-modal weighted average (SMWA) instead of full-band weighted average to reduce the over-smoothing problem in depth estimation.

Overall impression

Long tail is a typical problem in CNN-based depth estimation, for both monocular and disparity based, supervised or unsupervised methods. This point is echoed in pseudo lidar, pseudo lidar end to end and ForeSeE. The pseudo-lidar point with long tails confuses 3d object detectors.

DC focuses on depth completion while SMWA focuses on depth estimation from stereo pairs.

This paper seems to be heavily influenced by DC, including the soft one-hot encoding and cross entropy loss. But it did not acknowledge that.

Key ideas

Technical details

Notes