Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction

Sharma, Rajat; Schwandt, Tobias; Kunert, Christian; Urban, Steffen; Broll, Wolfgang

doi:10.5220/0010211600700079

Cited by 11 publications

(3 citation statements)

References 24 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are different types of RBL functions such as Dice loss and Jaccard loss, but it is not known whether RBL is more suitable for far‐field construction site scenes for segmentation. Moreover, two or more (distribution‐based and region‐based) loss functions can be combined to form a CPL function to obtain the performance improvement (Gupta et al., 2021; Sharma et al., 2021; Yeung et al., 2021). Nevertheless, there is no detailed investigation regarding the effectiveness of CPL functions for construction site scenes.…”

Section: Proposed Methodsmentioning

confidence: 99%

Impact of loss functions on semantic segmentation in far‐field monitoring

Chern

Nguyên

Asari

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

Although previous research laid the foundation for vision-based monitoring systems using convolutional neural networks (CNNs), too little attention has been paid to the challenges associated with data imbalance and varying object sizes in far-field monitoring. To fill the knowledge gap, this paper investigates various loss functions to design a customized loss function to address the challenges. Scaffold installation operations recorded by camcorders were selected as the subject of analysis in a far-field surveillance setting. It was confirmed that the data imbalance between the workers, hardhats, harnesses, straps, and hooks caused poor performances especially for small size objects. This problem was mitigated by employing a region-based loss and Focal loss terms in the loss function of segmentation models. The findings illustrate the importance of the loss function design in improving performance of CNN models for far-field construction site monitoring.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Impact of loss functions on semantic segmentation in far‐field monitoring

Chern

Nguyên

Asari

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…3) We design a refinement process to calculate loss and use it for back-propagation. There are many effective normal vector estimation methods, such as [31] using integral images for efficient boundary and covariance estimation, [32] [33] [34] [35] Use neural network to estimate. In our method, we tend to use the simplest method [36] because this method has lower time complexity and good accuracy.…”

Section: Proposed Methodsmentioning

confidence: 99%

Self-Supervised Segmentation for Terracotta Warrior Point Cloud (EGG-Net)

Geng

et al. 2022

IEEE Access

View full text Add to dashboard Cite

At present, our team focuses on the research of cultural relics restoration and fragment splicing. In the research process of terracotta warrior splicing, we find that the existing calibrated fragment data is relatively small, which is not enough for related research. Therefore, we need to calibrate and segment different parts of the intact terracotta warrior data and extract some data that we need to use in the future. However, at present, we are short of human resources. If we want to carry out manual calibration, it will take much time, bringing trouble to our future work. Therefore, we hope to design a method to automatically calibrate the terracotta warrior dataset with a small amount of calibrated data. The existing 3D neural network research mainly focuses on supervised classification, segmentation, and unsupervised reconstruction. We cannot find enough schemes to refer to, and the existing methods do not perform well on our terracotta warrior dataset. Therefore, in this article, we propose EGG-Net to solve this problem. EGG-Net is an end-to-end self-supervised model, and it consists of three modules. The first module is an encoder based on dynamic graph and edge convolution. We can extract point cloud features with this module. The second module, called segmenter, is based on multi-layer perceptron, adding labels to points and segmenting the point cloud. Finally, we designed a point refinement process as the third module. Point refinement can adjust the cluster label estimated by the neural network with superpoint. Our EGG-Net can backpropagate with the third module. We evaluate EGG-Net on the terracotta warrior data and ShapeNet Part by measuring the accuracy and the latency. The experiment result shows that our EGG-Net outperforms the state-of-the-art methods.

show abstract

“…This capability has significant implications for enhancing human-machine interaction in saliency-based approaches [3]. PCSD also finds broad applications across various domains, including reconstruction [4,5], compression [6,7], simplification [8,9], and viewpoint selection [10,11]. These applications leverage the insights provided by PCSD to drive advancements in point cloud analysis and processing.…”

mentioning

confidence: 99%