DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues

03/30/2021
by   Yifan Wang, et al.
1

Recently, significant progress has been made in single-view depth estimation thanks to increasingly large and diverse depth datasets. However, these datasets are largely limited to specific application domains (e.g. indoor, autonomous driving) or static in-the-wild scenes due to hardware constraints or technical limitations of 3D reconstruction. In this paper, we introduce the first depth dataset DynOcc consisting of dynamic in-the-wild scenes. Our approach leverages the occlusion cues in these dynamic scenes to infer depth relationships between points of selected video frames. To achieve accurate occlusion detection and depth order estimation, we employ a novel occlusion boundary detection, filtering and thinning scheme followed by a robust foreground/background classification method. In total our DynOcc dataset contains 22M depth pairs out of 91K frames from a diverse set of videos. Using our dataset we achieved state-of-the-art results measured in weighted human disagreement rate (WHDR). We also show that the inferred depth maps trained with DynOcc can preserve sharper depth boundaries.

READ FULL TEXT

page 1

page 4

page 6

page 7

page 8

research
08/12/2021

DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

We present a novel approach for estimating depth from a monocular camera...
research
02/28/2020

Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields

Current methods for depth map prediction from monocular images tend to p...
research
12/24/2019

DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling

We describe a technique that automatically generates plausible depth map...
research
11/29/2021

Instance-wise Occlusion and Depth Orders in Natural Scenes

In this paper, we introduce a new dataset, named InstaOrder, that can be...
research
05/02/2020

Towards Occlusion-Aware Multifocal Displays

The human visual system uses numerous cues for depth perception, includi...
research
04/20/2020

Robust 3D reconstruction of dynamic scenes from single-photon lidar using Beta-divergences

In this paper, we present a new algorithm for fast, online 3D reconstruc...
research
04/06/2021

Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries

Depth completion starts from a sparse set of known depth values and esti...

Please sign up or login with your details

Forgot password? Click here to reset