Deep feature-preserving normal estimation for point cloud filtering

Lu, Dening; Lu, Xuequan; Sun, Yangxing; Wang, Jun

doi:10.1016/j.cad.2020.102860

Cited by 80 publications

(47 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed algorithm was evaluated in comparison to known methods for point cloud filtering based on how precise they remove the interference artifacts. However, the SOR, ROR and the PointCleanNet filters are developed mainly for denoising and outliers removal [ 20 , 21 , 23 , 26 ]. In many cases, the interference artifact has specific statistical attributes and we cannot consider them as outliers.…”

Section: Discussionmentioning

confidence: 99%

Real-Time Interference Artifacts Suppression in Array of ToF Sensors

Volák

Bajzík

Janisova

et al. 2020

Sensors

View full text Add to dashboard Cite

Time of Flight (ToF) sensors are the source of various errors, including the multi-camera interference artifact caused by the parallel scanning mode of the sensors. This paper presents the novel Importance Map Based Median filtration algorithm for interference artifacts suppression, as the potential 3D filtration method. The approach is based on the processing of multiple depth frames, using the extraction of the interference region and application of the interpolation. Considering the limitations and good functionalities of proposed algorithm, the combination with some standard methods was suggested. Performance of the algorithm was evaluated on the dataset consisting of the real-world objects with different texture and morphology against popular filtering methods based on neural networks and statistics.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-Time Interference Artifacts Suppression in Array of ToF Sensors

Volák

Bajzík

Janisova

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The normal estimation of the point clouds has a long history in the research community, with publications on this topic dating back a long time [ 21 ], and it is still a hot topic with a considerable amount of publications in the last year focusing on learning-based methods [ 13 , 16 , 18 , 22 ].…”

Section: Background and Methodsmentioning

confidence: 99%

“…The idea of adaptive scale is also present for the Feature Pyramid Networks, which we adopted in our approach with the insight that they are able to mimic a multi-scale behaviour. These methods showed that a considerable enhancement can be achieved by using recent deep learning-based techniques for point clouds [ 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ]. Even though the deep learning-based methods require large amounts of training data, or may be prone to adversarial attacks or have exhaustive runtime, they are continuously rising in popularity and they gained appeal in low-level point cloud processing.…”

Section: Introductionmentioning

confidence: 99%

Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras

Molnár

Kelényi

Tamás

2021

Sensors

View full text Add to dashboard Cite

In this paper, an efficient normal estimation and filtering method for depth images acquired by Time-of-Flight (ToF) cameras is proposed. The method is based on a common feature pyramid networks (FPN) architecture. The normal estimation method is called ToFNest, and the filtering method ToFClean. Both of these low-level 3D point cloud processing methods start from the 2D depth images, projecting the measured data into the 3D space and computing a task-specific loss function. Despite the simplicity, the methods prove to be efficient in terms of robustness and runtime. In order to validate the methods, extensive evaluations on public and custom datasets were performed. Compared with the state-of-the-art methods, the ToFNest and ToFClean algorithms are faster by an order of magnitude without losing precision on public datasets.

show abstract

“…Therefore, the purpose of point cloud filtering is to filter outliers and noise points as much as possible [34][35][36], reducing the influence of g S and e β on point cloud fitting, so as to imp rove the integrity of the geometric characteristics of the object itself. Aiming at the problems of outliers and noise in raw point cloud obtained by LiDA R [37][38][39][40], outlier detection methods [41][42][43] were proposed, which has good effect on isolated discrete points and sparse cluster points, but can not be applied for noise points attached to the surface of target point cloud. The point cloud obtained by LiDAR has the characteristics of large scale and low p recision, while the point cloud obtained by DFP has the characteristics of s mall scale, high precision and high density.…”

Section: B Bilateral Filtering For Cylinder Point Cloudmentioning

confidence: 99%

Cutting Plane Based Cylinder Fitting Method With Incomplete Point Cloud Data for Digital Fringe Projection

Xue

2020

IEEE Access

View full text Add to dashboard Cite

Benefiting fro m the characteristics of full field scanning, high resolution and high precision, digital fringe projection measurement technology has been widely used in three -dimensional measurement. For the cylinder pose detection, due to the influence of occlusion and noise, the obtained three-dimensional point cloud informat ion is usually inco mplete, resulting in the unreliable object parameters after point cloud fitting. In view of the above problems, a cy linder fitting method with inco mplete point clou d data based on the cutting plane is proposed. Firstly, the point cloud is processed by bilateral filtering method to reduce the influence of outliers and noise points. Then, according to the principle of forming ellipse on cylinder cutting plane, some equidistant cutting planes are selected. At the same time, in order to reduce the influence of outliers on fitting, the random sampling consistency algorith m is used for ellipse fitting with the points on each cutting plane, that is, the ellipse parameters co rresponding to each cutting plane can be obtained. Finally, random sampling consistency algorithm is applied for cylinder axis fitting with the ellipse centers of all the cutting planes, calculating the axis vector of the cylinder. Thus, the parameters of the cylinder detected are obtained. The experimental results of stepped cylinder with d iffuse reflection and metal cylinder show the effectiveness and high precision of the proposed method.INDEX TERMS digital fringe projection, cutting plane, cylinder fitting, incomplete point cloud, ellipse fitting.

show abstract

Deep feature-preserving normal estimation for point cloud filtering

Cited by 80 publications

References 35 publications

Real-Time Interference Artifacts Suppression in Array of ToF Sensors

Real-Time Interference Artifacts Suppression in Array of ToF Sensors

Feature Pyramid Network Based Efficient Normal Estimation and Filtering for Time-of-Flight Depth Cameras

Cutting Plane Based Cylinder Fitting Method With Incomplete Point Cloud Data for Digital Fringe Projection

Contact Info

Product

Resources

About