Denoising point sets via <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.gif" overflow="scroll"><mml:msub><mml:mrow><mml:mi>L</mml:mi></mml:mrow><mml:mrow><mml:mn>0</mml:mn></mml:mrow></mml:msub></mml:math> minimization

247

196

Point clouds obtained with 3D scanners or by image‐based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g. jets or MLS surfaces), local or non‐local averaging or on statistical assumptions about the underlying noise model. In contrast, we develop a simple data‐driven method for removing outliers and reducing noise in unordered point clouds. We base our approach on a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties in point clouds. Our method first classifies and discards outlier samples, and then estimates correction vectors that project noisy points onto the original clean surfaces. The approach is efficient and robust to varying amounts of noise and outliers, while being able to handle large densely sampled point clouds. In our extensive evaluation, both on synthetic and real data, we show an increased robustness to strong noise levels compared to various state‐of‐the‐art methods, enabling accurate surface reconstruction from extremely noisy real data obtained by range scans. Finally, the simplicity and universality of our approach makes it very easy to integrate in any existing geometry processing pipeline. Both the code and pre‐trained networks can be found on the project page (https://github.com/mrakotosaon/pointcleannet).

Section: Related Workmentioning

confidence: 99%

PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds

Rakotosaona

Barbera

Guerrero

et al. 2019

247

196

“…Moreover, a higher robustness to outliers is usually obtained using a larger neighborhood, which makes sharp features even smoother. Minimizing the ℓ 1 [ASGCO10] or ℓ 0 norm [SSW15] is robust to sharp features but quite slow. Moving least squares [ABCO*03, PKKG03] and local kernel regression [ÖGG09] estimate normals as the gradient of an implicit surface, preserving sharp features, but requiring reliable normal priors as input.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning for Robust Normal Estimation in Unstructured Point Clouds

Boulch

Marlet

2016

119

Normal estimation in point clouds is a crucial first step for numerous algorithms, from surface reconstruction and scene understanding to rendering. A recurrent issue when estimating normals is to make appropriate decisions close to sharp features, not to smooth edges, or when the sampling density is not uniform, to prevent bias. Rather than resorting to manually‐designed geometric priors, we propose to learn how to make these decisions, using ground‐truth data made from synthetic scenes. For this, we project a discretized Hough space representing normal directions onto a structure amenable to deep learning. The resulting normal estimation method outperforms most of the time the state of the art regarding robustness to outliers, to noise and to point density variation, in the presence of sharp edges, while remaining fast, scaling up to millions of points.

“…8 (a)). This side-effect is also encountered in [LWC * 18] and [SSW15] for the reason that points near edges are attracted to and accumulated around edges in order to achieve the minimal value of Eq. 9.…”

Section: Position Updatingmentioning

confidence: 90%

Reliable Rolling‐guided Point Normal Filtering for Surface Texture Removal

Sun

Chen

Qin

et al. 2019

Semantic surface decomposition (SSD) facilitates various geometry processing and product re‐design tasks. Filter‐based techniques are meaningful and widely used to achieve the SSD, which however often leads to surface either under‐fitting or over‐fitting. In this paper, we propose a reliable rolling‐guided point normal filtering method to decompose textures from a captured point cloud surface. Our method is built on the geometry assumption that 3D surfaces are comprised of an underlying shape (US) and a variety of bump ups and downs (BUDs) on the US. We have three core contributions. First, by considering the BUDs as surface textures, we present a RANSAC‐based sub‐neighborhood detection scheme to distinguish the US and the textures. Second, to better preserve the US (especially the prominent structures), we introduce a patch shift scheme to estimate the guidance normal for feeding the rolling‐guided filter. Third, we formulate a new position updating scheme to alleviate the common uneven distribution of points. Both visual and numerical experiments demonstrate that our method is comparable to state‐of‐the‐art methods in terms of the robustness of texture removal and the effectiveness of the underlying shape preservation.