Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

NeurIPS 2019 Jia-Wang BianZhichao LiNaiyan WangHuangying ZhanChunhua ShenMing-Ming ChengIan Reid

Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in geometric image reconstruction... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Monocular Depth Estimation KITTI Eigen split SC-SfMLearner_CS+K absolute relative error 0.128 # 16
Monocular Depth Estimation KITTI Eigen split SC-SfMLearner absolute relative error 0.137 # 19
Monocular Depth Estimation KITTI Eigen split SC-SfMLearner-r50 absolute relative error 0.115 # 12

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet