IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation

12/20/2019
by   Qiang Wang, et al.
2

Indoor robotics localization, navigation and interaction heavily rely on scene understanding and reconstruction. Compared to monocular vision which usually does not explicitly introduce any geometrical constraint, stereo vision based schemes are more promising and robust to produce accurate geometrical information, such as surface normal and depth/disparity. Besides, deep learning models trained with large-scale datasets have shown their superior performance in many stereo vision tasks. However, existing stereo datasets rarely contain the high-quality surface normal and disparity ground truth, which hardly satisfy the demand of training a prospective deep model for indoor scenes. To this end, we introduce a large-scale synthetic indoor robotics stereo (IRS) dataset with over 100K stereo RGB images and high-quality surface normal and disparity maps. Leveraging the advanced rendering techniques of our customized rendering engine, the dataset is considerably close to the real-world captured images and covers several visual effects, such as brightness changes, light reflection/transmission, lens flare, vivid shadow, etc. We compare the data distribution of IRS with existing stereo datasets to illustrate the typical visual attributes of indoor scenes. In addition, we present a new deep model DispNormNet to simultaneously infer surface normal and disparity from stereo images. Compared to existing models trained on other datasets, DispNormNet trained with IRS produces much better estimation of surface normal and disparity for indoor scenes.

READ FULL TEXT

page 1

page 3

page 4

page 6

research
11/30/2021

PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction

Stereo matching is an important task in computer vision which has drawn ...
research
04/01/2017

Configurable, Photorealistic Image Rendering and Ground Truth Synthesis by Sampling Stochastic Grammars Representing Indoor Scenes

We propose the configurable rendering of massive quantities of photoreal...
research
11/19/2022

Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics

High-quality estimation of surface normal can help reduce ambiguity in m...
research
05/17/2020

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator

Over the past decade, significant efforts have been made to improve the ...
research
07/14/2022

Egocentric Scene Understanding via Multimodal Spatial Rectifier

In this paper, we study a problem of egocentric scene understanding, i.e...
research
09/16/2019

360^o Surface Regression with a Hyper-Sphere Loss

Omnidirectional vision is becoming increasingly relevant as more efficie...
research
12/12/2020

Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces

This paper presents an uncalibrated deep neural network framework for th...

Please sign up or login with your details

Forgot password? Click here to reset