Monocular Depth Distribution Alignment with Low Computation

03/09/2022
by   Fei Sheng, et al.
0

The performance of monocular depth estimation generally depends on the amount of parameters and computational cost. It leads to a large accuracy contrast between light-weight networks and heavy-weight networks, which limits their application in the real world. In this paper, we model the majority of accuracy contrast between them as the difference of depth distribution, which we call "Distribution drift". To this end, a distribution alignment network (DANet) is proposed. We firstly design a pyramid scene transformer (PST) module to capture inter-region interaction in multiple scales. By perceiving the difference of depth features between every two regions, DANet tends to predict a reasonable scene structure, which fits the shape of distribution to ground truth. Then, we propose a local-global optimization (LGO) scheme to realize the supervision of global range of scene depth. Thanks to the alignment of depth distribution shape and scene depth range, DANet sharply alleviates the distribution drift, and achieves a comparable performance with prior heavy-weight methods, but uses only 1 on two datasets, namely the widely used NYUDv2 dataset and the more challenging iBims-1 dataset, demonstrate the effectiveness of our method. The source code is available at https://github.com/YiLiM1/DANet.

READ FULL TEXT

page 1

page 2

page 3

page 6

research
07/13/2019

Structure-Aware Residual Pyramid Network for Monocular Depth Estimation

Monocular depth estimation is an essential task for scene understanding....
research
07/14/2020

360^∘ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedron

In this study, we present a method for all-around depth estimation from ...
research
03/21/2023

Monocular Visual-Inertial Depth Estimation

We present a visual-inertial depth estimation pipeline that integrates m...
research
02/26/2021

Boundary-induced and scene-aggregated network for monocular depth prediction

Monocular depth prediction is an important task in scene understanding. ...
research
04/05/2022

P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior

Monocular depth estimation is vital for scene understanding and downstre...
research
07/20/2022

Learning Depth from Focus in the Wild

For better photography, most recent commercial cameras including smartph...
research
06/12/2023

H-SLAM: Hybrid Direct-Indirect Visual SLAM

The recent success of hybrid methods in monocular odometry has led to ma...

Please sign up or login with your details

Forgot password? Click here to reset