SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception

CVPR 2019 Yue MengYongxi LuAman RajSamuel SunarjoRui GuoTara JavidiGaurav BansalDinesh Bharadia

Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Monocular Depth Estimation KITTI Eigen split SIGNet absolute relative error 0.133 # 15