Point Cloud Upsampling via Cascaded Refinement Network

  title={Point Cloud Upsampling via Cascaded Refinement Network},
  author={Hang Du and Xuejun Yan and Jingjing Wang and Di Xie and Shiliang Pu},
  booktitle={Asian Conference on Computer Vision},
Point cloud upsampling focuses on generating a dense, uniform and proximity-to-surface point set. Most previous approaches accomplish these objectives by carefully designing a single-stage network, which makes it still challenging to generate a high-fidelity point distribution. Instead, upsampling point cloud in a coarse-to-fine manner is a decent solution. However, existing coarse-to-fine upsampling methods require extra training strategies, which are complicated and time-consuming during the… 

Figures and Tables from this paper



Point Cloud Upsampling via Disentangled Refinement

  • Ruihui LiXianzhi LiP. HengChi-Wing Fu
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
This work proposes to disentangle the task based on its multi-objective nature and formulate two cascaded sub-networks, a dense generator and a spatial refiner, and designs a pair of local and global refinement units in the spatial refiners to evolve a coarse feature map.

Deep Magnification-Flexible Upsampling Over 3D Point Clouds

This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes by taking advantage of the linear approximation theorem and designing a lightweight neural network to adaptively learn unified and sorted interpolation weights as well as the high-order refinements.

Cascaded Refinement Network for Point Cloud Completion

This work proposes a cascaded refinement network together with a coarse-to-fine strategy to synthesize the detailed object shapes and designs a patch discriminator that guarantees every local area has the same pattern with the ground truth to learn the complicated point distribution.

PU-Net: Point Cloud Upsampling Network

A data-driven point cloud upsampling technique to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space, which shows that its upsampled points have better uniformity and are located closer to the underlying surfaces.

Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud

A novel method called “Meta-PU” is proposed to first support point cloud upsampling of arbitrary scale factors with a single model and even outperforms the existing methods trained for a specific scale factor only.

PC2-PU: Patch Correlation and Position Correction for Effective Point Cloud Upsampling

This paper takes adjacent patches as input and introduces a Patch Correlation Unit to explore the shape correspondence between them for effective upsampling, and proposes a Position Correction Unit to mitigate the effects of outliers and noisy points.

SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering

  • Yifan ZhaoLe HuiJin Xie
  • Computer Science, Environmental Science
    ACM Multimedia
  • 2021
A self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth to exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images.

Progressive Point Cloud Deconvolution Generation Network

An effective point cloud generation method that can generate multi-resolution point clouds of the same shape from a latent vector is proposed and a shape-preserving adversarial loss is proposed to train the point cloud deconvolution generation network.

PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling

This paper addresses the problem of generating uniform dense point clouds to describe the underlying geometric structures from given sparse point clouds. Due to the irregular and unordered nature,

PU-GAN: A Point Cloud Upsampling Adversarial Network

A new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces.