Feature-based RGB-D camera pose optimization for real-time 3D reconstruction

Wang, Chao; Guo, Xiaohu

doi:10.1007/s41095-016-0072-2

Cited by 15 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to monocular images, most object pose reconstruction approaches based on RGB-D data rely on features or descriptors which are used to infer an object's pose. While some utilize conventional features such as SURF ( Wang and Guo, 2017 ) other approaches propose a set of distinct features on the RGB-D data using deep learning ( Zeng et al, 2017;Bo et al, 2014;Kehl et al, 2016 ). The conversion of features to pose is solved very differently, ranging from 6D object pose voting to the minimization of an energy function.…”

Section: Image-based Pose Reconstructionmentioning

confidence: 99%

Marker-free surgical navigation of rod bending using a stereo neural network and augmented reality in spinal fusion

Atzigen

Liebmann

Hoch

et al. 2022

Medical Image Analysis

View full text Add to dashboard Cite

Section: Image-based Pose Reconstructionmentioning

confidence: 99%

Marker-free surgical navigation of rod bending using a stereo neural network and augmented reality in spinal fusion

Atzigen

Liebmann

Hoch

et al. 2022

Medical Image Analysis

View full text Add to dashboard Cite

“…1.2.3 Accumulated error. Apart from focusing on the error sourced from the frame-by-frame registration, methods have been developed to correct the error accumulation in camera pose estimation and global 3D model in both online [Cao et al 2018;Wang and Guo 2017;Wasenmüller et al 2016;Whelan et al 2012] and offline [Choi et al 2015;Li et al 2013;] mode, where the offline methods are time-consuming.…”

Section: Related Workmentioning

confidence: 99%

HRBF-Fusion: Accurate 3D Reconstruction from RGB-D Data Using On-the-fly Implicits

Nan

Zhou

et al. 2022

ACM Trans. Graph.

View full text Add to dashboard Cite

Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point- or voxel-based), existing approaches suffer from the accumulation of errors in camera tracking and distortion in the reconstruction, which leads to an unsatisfactory 3D reconstruction. In this paper, we present a method using on-the-fly implicits of Hermite Radial Basis Functions (HRBFs) as a continuous surface representation for camera tracking in an existing RGB-D fusion framework. Furthermore, curvature estimation and confidence evaluation are coherently derived from the inherent surface properties of the on-the-fly HRBF implicits, which devote to a data fusion with better quality. We argue that our continuous but on-the-fly surface representation can effectively mitigate the impact of noise with its robustness and constrain the reconstruction with inherent surface smoothness when being compared with discrete representations. Experimental results on various real-world and synthetic datasets demonstrate that our HRBF-fusion outperforms the state-of-the-art approaches in terms of tracking robustness and reconstruction accuracy.

show abstract

“…However, there are many alternative feature sparse feature descriptors such as SURF [BTVG06], ORB [RRKB11], or more recently even learned descriptors [HLJ*15,YTLF16,ZSN*17]. Another approach is to search for correspondences across multiple frames [WG17].…”

Section: Static Scene Reconstructionmentioning

confidence: 99%

State of the Art on 3D Reconstruction with RGB‐D Cameras

Zollhöfer

Stotko

Görlitz

et al. 2018

Computer Graphics Forum

263

123

View full text Add to dashboard Cite

The advent of affordable consumer grade RGB‐D cameras has brought about a profound advancement of visual scene reconstruction methods. Both computer graphics and computer vision researchers spend significant effort to develop entirely new algorithms to capture comprehensive shape models of static and dynamic scenes with RGB‐D cameras. This led to significant advances of the state of the art along several dimensions. Some methods achieve very high reconstruction detail, despite limited sensor resolution. Others even achieve real‐time performance, yet possibly at lower quality. New concepts were developed to capture scenes at larger spatial and temporal extent. Other recent algorithms flank shape reconstruction with concurrent material and lighting estimation, even in general scenes and unconstrained conditions. In this state‐of‐the‐art report, we analyze these recent developments in RGB‐D scene reconstruction in detail and review essential related work. We explain, compare, and critically analyze the common underlying algorithmic concepts that enabled these recent advancements. Furthermore, we show how algorithms are designed to best exploit the benefits of RGB‐D data while suppressing their often non‐trivial data distortions. In addition, this report identifies and discusses important open research questions and suggests relevant directions for future work.

show abstract

Feature-based RGB-D camera pose optimization for real-time 3D reconstruction

Cited by 15 publications

References 29 publications

Marker-free surgical navigation of rod bending using a stereo neural network and augmented reality in spinal fusion

Marker-free surgical navigation of rod bending using a stereo neural network and augmented reality in spinal fusion

HRBF-Fusion: Accurate 3D Reconstruction from RGB-D Data Using On-the-fly Implicits

State of the Art on 3D Reconstruction with RGB‐D Cameras

Contact Info

Product

Resources

About