FusionMLS: Highly dynamic 3D reconstruction with consumer-grade RGB-D cameras

Meerits, Siim; Thomas, Diego; Nozick, Vincent; Saitō, Hideo

doi:10.1007/s41095-018-0121-0

Cited by 14 publications

(17 citation statements)

References 29 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the pioneering work of KinectFusion [Newcombe et al 2011] that applied a Truncated Signed Distance Field (TSDF) [Curless and Levoy 1996] for modeling integration, volumetric representation has demonstrated promising results for reconstructing small-scale scenes. Because of its implementation on GPU for real-time tracking and fusion, volumetric representation becomes more and more popular [Chen et al 2013;Meerits et al 2018;Niessner et al 2013]. The original uniform-grid KinectFusion has a fundamental limitation (i.e., the lack of scalability), which leads to expensive memory consumption for reconstructing ine details.…”

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

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

show abstract

“…DynamicFusion [22] uses dual quaternions to represent deformations for better quality of transformation blending. Some other methods [3,4,20] use multiple cameras to reduce occluded regions and improve motion tracking.…”

Section: Template-based Non-rigid Registrationmentioning

confidence: 99%

Robust Template-Based Non-Rigid Motion Tracking Using Local Coordinate Regularization

Zhao

Xiao

et al. 2020

2020 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

In this paper, we propose our template-based non-rigid registration algorithm to address the misalignments in the frame-to-frame motion tracking with single or multiple commodity depth cameras. We analyze the deformation in the local coordinates of neighboring nodes and use this differential representation to formulate the regularization term for the deformation field in our non-rigid registration. The local coordinate regularizations vary for each pair of neighboring nodes based on the tracking status of the surface regions. We propose our tracking strategies for different surface regions to minimize misalignments and reduce error accumulation. This method can thus preserve local geometric features and prevent undesirable distortions. Moreover, we introduce a geodesic-based correspondence estimation algorithm to align surfaces with large displacements. Finally, we demonstrate the effectiveness of our proposed method with detailed experiments.

show abstract

“…In addition to optical sensors, depth sensors are also widely used to capture dynamic scenes [7], including human pose [8,9] or attitude [5]. Such approach can take advantage of direct depth measurements by light set-up with few sensors [10,11].…”

Section: Related Workmentioning

confidence: 99%

A Motion Capture System for Sport Performance Analysis Based on Inexpensive RGB-D Sensors

André¹,

Lemaître²,

Voiry³

et al. 2019

Proceedings of 3DBODY.TECH 2019 - 10th International Conference and Exhibition on 3D Body Scanning and Processing Technologies,

View full text Add to dashboard Cite

Motion capture for gesture and performance analysis in sports usually requires tracking of several anatomical landmarks with high spatial accuracy and sampling frequency. In addition, a model of the outer surface of the body can also be useful, e.g. for aerodynamic studies. In this context, we developed a motion capture system based on four inexpensive commercial RGB-D cameras. Our system produces both skeletal poses and 3D meshes of moving human bodies at high frequency with good accuracy.

show abstract

FusionMLS: Highly dynamic 3D reconstruction with consumer-grade RGB-D cameras

Cited by 14 publications

References 29 publications

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

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

Robust Template-Based Non-Rigid Motion Tracking Using Local Coordinate Regularization

A Motion Capture System for Sport Performance Analysis Based on Inexpensive RGB-D Sensors

Contact Info

Product

Resources

About