Submitted by
Chaoqiang Zhao
Authors
Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, Xin Qiao, Yang Tang, Stefano Mattoccia
Venue
arxiv
Abstract
A transformer based monocular depth estimation framework for robust estimation under different scenes.
Runtime
38 ms
External data used
NO
Links
  • There is no link to the paper.
  • There is no link to the code.
  • There is no link to the project website.
Number of submissions
1

Detailed results
MetricAlldaysunsetsnowrainnight
Scale invariant logarithmic error 1.24 0.86 1.38 1.58 1.19 1.17
Absolute squared error [%] 37.73 19.03 43.15 47.69 32.92 45.84
Root mean squared error of the inverse depth 162.90 81.80 196.93 256.92 131.81 147.03