PCPN<scp>et</scp> Learning Local Shape Properties from Raw Point Clouds

Guerrero, Paul; Kleiman, Yanir; Ovsjanikov, Maks; Mitra, Niloy J.

doi:10.1111/cgf.13343

Cited by 288 publications

(267 citation statements)

References 30 publications

Supporting

Mentioning

267

Contrasting

Order By: Relevance

“…Additionally, processing dense point clouds becomes more difficult, due to high memory complexity. In settings such as ours, local methods such as PCPNet [GKOM18] perform better. Both steps of our approach are based on the network architecture described in this method, due to its relative simplicity and competitive performance.…”

Section: Overviewmentioning

confidence: 93%

“…Unlike these techniques, our goal is to train a general-purpose method for removing outliers and denoising point clouds, corrupted with potentially very high levels of structured noise. For this, inspired by the success of PCPNet [GKOM18] for normal and curvature estimation, we propose a simple framework aimed at learning to both classify outliers and to displace noisy point clouds by applying an adapted architecture to point cloud patches. We show through extensive experimental evaluation that our approach can handle a wide range of artefacts, while being applicable to dense point clouds, without any user intervention.…”

Section: Learning In Point Cloudsmentioning

confidence: 99%

See 1 more Smart Citation

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

Rakotosaona

Barbera

Guerrero

et al. 2019

Computer Graphics Forum

Self Cite

247

196

View full text Add to dashboard Cite

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).

show abstract

Section: Overviewmentioning

confidence: 93%

Section: Learning In Point Cloudsmentioning

confidence: 99%

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

Rakotosaona

Barbera

Guerrero

et al. 2019

Computer Graphics Forum

Self Cite

247

196

View full text Add to dashboard Cite

show abstract

“…As observed in many point denoising works [Guerrero et al 2018;Huang et al 2009;Öztireli et al 2009], finding the right normal is the key for obtaining clean surfaces. Hence we efficiently utilize the improved normals even if the point positions are not being updated, in that we directly update the point positions using the gradient from the regularization terms ∂ L p ∂p k and ∂ L r ∂p k .…”

Section: Alternating Normal and Point Updatementioning

confidence: 97%

Differentiable surface splatting for point-based geometry processing

et al. 2019

View full text Add to dashboard Cite

Fig. 1. Using our differentiable point-based renderer, scene content can be optimized to match target rendering. Here, the positions and normals of points are optimized in order to reproduce the reference rendering of the Stanford bunny. It successfully deforms a sphere to a target bunny model, capturing both large scale and fine-scale structures. From left to right are the input points, the results of iteration 18, 57, 198, 300, and the target.We propose Differentiable Surface Splatting (DSS), a high-fidelity differentiable renderer for point clouds. Gradients for point locations and normals are carefully designed to handle discontinuities of the rendering function. Regularization terms are introduced to ensure uniform distribution of the points on the underlying surface. We demonstrate applications of DSS to inverse rendering for geometry synthesis and denoising, where large scale topological changes, as well as small scale detail modifications, are accurately and robustly handled without requiring explicit connectivity, outperforming state-of-the-art techniques. The data and code are at https://github.com/yifita/DSS.

show abstract

“…Deep learning for point-set shapes. Recently, several deep neural networks, including PointNET [Qi et al 2017a], PointNET++ [Qi et al 2017b], PCPNET [Guerrero et al 2018], PointCNN [Li et al 2018], and PCNN [Atzmon et al 2018], have been developed for feature learning over point clouds. Generative models of pointset shapes [Achlioptas et al 2018;Fan et al 2017] and supervised, general-purpose point-set transforms [Yin et al 2018] have also been proposed.…”

Section: Related Workmentioning

confidence: 99%

Logan

et al. 2019

View full text Add to dashboard Cite

Fig. 1. We present LOGAN, a deep neural network which learns general-purpose shape transforms from unpaired domains. By altering only the two input data domains for training, without changing the network architecture or any hyper-parameters, LOGAN can transform between chairs and tables, from cross-sectional profiles to surfaces, as well as adding arms to chairs. It can also learn both style-preserving content transfer (letters R → P , A → H , in different font styles) and content-preserving style transfer (wide to narrow S , thick to thin I , thin to thick G, and italic to non-italic A.)We introduce LOGAN, a deep neural network aimed at learning generalpurpose shape transforms from unpaired domains. The network is trained on two sets of shapes, e.g., tables and chairs, while there is neither a pairing between shapes from the domains as supervision nor any point-wise correspondence between any shapes. Once trained, LOGAN takes a shape from one domain and transforms it into the other. Our network consists of an autoencoder to encode shapes from the two input domains into a common latent space, where the latent codes concatenate multi-scale shape features, resulting in an overcomplete representation. The translator is based on a generative adversarial network (GAN), operating in the latent space, where an adversarial loss enforces cross-domain translation while a feature preservation loss ensures that the right shape features are preserved for a natural shape transform. We conduct ablation studies to validate each of our key network designs and demonstrate superior capabilities in unpaired shape transforms on a variety of examples over baselines and state-of-the-art approaches. We show that LOGAN is able to learn what shape features to preserve during shape translation, either local or non-local, whether content or style, depending solely on the input domains for training.

show abstract

PCPNet Learning Local Shape Properties from Raw Point Clouds

Cited by 288 publications

References 30 publications

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

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

Differentiable surface splatting for point-based geometry processing

Logan

Contact Info

Product

Resources

About