Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling

High-resolution RGB-D sensors are widely used in computer vision, manufacturing, and robotics. The depth maps from these sensors have inherently high measurement uncertainty that includes both systematic and non-systematic noise. These noisy depth estimates degrade the quality of scans, resulting in...

Full description

Saved in:
Bibliographic Details
Main Authors: Fahira Afzal Maken, Sundaram Muthu, Chuong Nguyen, Changming Sun, Jinguang Tong, Shan Wang, Russell Tsuchida, David Howard, Simon Dunstall, Lars Petersson
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/3/950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850068392876179456
author Fahira Afzal Maken
Sundaram Muthu
Chuong Nguyen
Changming Sun
Jinguang Tong
Shan Wang
Russell Tsuchida
David Howard
Simon Dunstall
Lars Petersson
author_facet Fahira Afzal Maken
Sundaram Muthu
Chuong Nguyen
Changming Sun
Jinguang Tong
Shan Wang
Russell Tsuchida
David Howard
Simon Dunstall
Lars Petersson
author_sort Fahira Afzal Maken
collection DOAJ
description High-resolution RGB-D sensors are widely used in computer vision, manufacturing, and robotics. The depth maps from these sensors have inherently high measurement uncertainty that includes both systematic and non-systematic noise. These noisy depth estimates degrade the quality of scans, resulting in less accurate 3D reconstruction, making them unsuitable for some high-precision applications. In this paper, we focus on quantifying the uncertainty in the depth maps of high-resolution RGB-D sensors for the purpose of improving 3D reconstruction accuracy. To this end, we estimate the noise model for a recent high-precision RGB-D structured light sensor called Zivid when mounted on a robot arm. Our proposed noise model takes into account the measurement distance and angle between the sensor and the measured surface. We additionally analyze the effect of background light, exposure time, and the number of captures on the quality of the depth maps obtained. Our noise model seamlessly integrates with well-known classical and modern neural rendering-based algorithms, from KinectFusion to Point-SLAM methods using bilinear interpolation as well as 3D analytical functions. We collect a high-resolution RGB-D dataset and apply our noise model to improve tracking and produce higher-resolution 3D models.
format Article
id doaj-art-720dbe35c6324937aeb8dbc3935c18c7
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-720dbe35c6324937aeb8dbc3935c18c72025-08-20T02:48:05ZengMDPI AGSensors1424-82202025-02-0125395010.3390/s25030950Improving 3D Reconstruction Through RGB-D Sensor Noise ModelingFahira Afzal Maken0Sundaram Muthu1Chuong Nguyen2Changming Sun3Jinguang Tong4Shan Wang5Russell Tsuchida6David Howard7Simon Dunstall8Lars Petersson9Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaData61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT 2601, AustraliaHigh-resolution RGB-D sensors are widely used in computer vision, manufacturing, and robotics. The depth maps from these sensors have inherently high measurement uncertainty that includes both systematic and non-systematic noise. These noisy depth estimates degrade the quality of scans, resulting in less accurate 3D reconstruction, making them unsuitable for some high-precision applications. In this paper, we focus on quantifying the uncertainty in the depth maps of high-resolution RGB-D sensors for the purpose of improving 3D reconstruction accuracy. To this end, we estimate the noise model for a recent high-precision RGB-D structured light sensor called Zivid when mounted on a robot arm. Our proposed noise model takes into account the measurement distance and angle between the sensor and the measured surface. We additionally analyze the effect of background light, exposure time, and the number of captures on the quality of the depth maps obtained. Our noise model seamlessly integrates with well-known classical and modern neural rendering-based algorithms, from KinectFusion to Point-SLAM methods using bilinear interpolation as well as 3D analytical functions. We collect a high-resolution RGB-D dataset and apply our noise model to improve tracking and produce higher-resolution 3D models.https://www.mdpi.com/1424-8220/25/3/950sensor noise modeling3D reconstructionRGB-D fusion
spellingShingle Fahira Afzal Maken
Sundaram Muthu
Chuong Nguyen
Changming Sun
Jinguang Tong
Shan Wang
Russell Tsuchida
David Howard
Simon Dunstall
Lars Petersson
Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling
Sensors
sensor noise modeling
3D reconstruction
RGB-D fusion
title Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling
title_full Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling
title_fullStr Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling
title_full_unstemmed Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling
title_short Improving 3D Reconstruction Through RGB-D Sensor Noise Modeling
title_sort improving 3d reconstruction through rgb d sensor noise modeling
topic sensor noise modeling
3D reconstruction
RGB-D fusion
url https://www.mdpi.com/1424-8220/25/3/950
work_keys_str_mv AT fahiraafzalmaken improving3dreconstructionthroughrgbdsensornoisemodeling
AT sundarammuthu improving3dreconstructionthroughrgbdsensornoisemodeling
AT chuongnguyen improving3dreconstructionthroughrgbdsensornoisemodeling
AT changmingsun improving3dreconstructionthroughrgbdsensornoisemodeling
AT jinguangtong improving3dreconstructionthroughrgbdsensornoisemodeling
AT shanwang improving3dreconstructionthroughrgbdsensornoisemodeling
AT russelltsuchida improving3dreconstructionthroughrgbdsensornoisemodeling
AT davidhoward improving3dreconstructionthroughrgbdsensornoisemodeling
AT simondunstall improving3dreconstructionthroughrgbdsensornoisemodeling
AT larspetersson improving3dreconstructionthroughrgbdsensornoisemodeling