Structure-Attentioned Memory Network for Monocular Depth Estimation

10 Sep 2019 Jing Zhu Yunxiao Shi Mengwei Ren Yi Fang Kuo-Chin Lien Junli Gu

Monocular depth estimation is a challenging task that aims to predict a corresponding depth map from a given single RGB image. Recent deep learning models have been proposed to predict the depth from the image by learning the alignment of deep features between the RGB image and the depth domains... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Monocular Depth Estimation KITTI Eigen split SOM absolute relative error 0.097 # 9
Monocular Depth Estimation NYU-Depth V2 SOM RMSE 0.604 # 20

Methods used in the Paper


METHOD TYPE
SOM
Clustering
Memory Network
Working Memory Models