Deep Ordinal Regression Network for Monocular Depth Estimation

CVPR 2018 Huan FuMingming GongChaohui WangKayhan BatmanghelichDacheng Tao

Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep convolutional neural networks (DCNNs)... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Monocular Depth Estimation KITTI Eigen split DORN absolute relative error 0.072 # 2
Monocular Depth Estimation NYU-Depth V2 DORN RMSE 0.509 # 6

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