GRNet: Gridding Residual Network for Dense Point Cloud Completion

  title={GRNet: Gridding Residual Network for Dense Point Cloud Completion},
  author={Haozhe Xie and Hongxun Yao and Shangchen Zhou and Jiageng Mao and Shengping Zhang and Wenxiu Sun},
Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which may cause the loss of details because the structural and context of point clouds are not fully considered. To solve this problem, we introduce 3D grids as intermediate representations to regularize unordered point clouds. We therefore propose a novel Gridding… 

PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths

A novel neural network, named PMP-Net, is designed to mimic the behavior of an earth mover, which predicts a unique point moving path for each point according to the constraint of total point moving distances.

HyperPocket: Generative Point Cloud Completion

This work reformulates the problem of point cloud completion into an objects hallucination task and introduces a novel autoencoder-based architecture called HyperPocket that disentangles latent representations and enables the generation of multiple variants of the completed 3D point clouds.

Variational Relational Point Completion Network

A variational framework, Variational Relational point Completion network (VRC-Net), with two appealing properties: Probabilistic Modeling and Relational Enhancement, which shows great generalizability and robustness on real-world point cloud scans.

A Self-supervised Cascaded Refinement Network for Point Cloud Completion

This work proposes a self-supervised object completion method, which optimizes the training procedure solely on the partial input without utilizing the fully-complete ground truth, and proposes a cascaded refinement network (CRN) with a coarse-to-fine strategy to synthesize the complete objects.

Deep Learning for 3D Point Cloud Understanding: A Survey

This paper summarizes recent remarkable research contributions in this area from several different directions (classification, segmentation, detection, tracking, flow estimation, registration, augmentation and completion), together with commonly used datasets, metrics and state-of-the-art performances.

ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion

The Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior and an iterative refinement unit is designed to generate complete shapes with fine-grained details by integrating prior information.

Cloud Transformers

A new versatile building block for deep point cloud processing architectures that combines the ideas of spatial transformers and multi-view CNNs with the efficiency of standard convolutional layers in two and three-dimensional dense grids is presented.

Learning multiscale spatial context for three-dimensional point cloud semantic segmentation

A multiscale spatial context feature learning is used in an end-to-end approach for 3D point cloud semantic segmentation and a local feature fusion learning block is introduced to the hidden layers in the network to improve its feature learning capability.

View-Guided Point Cloud Completion

This paper addresses this task by introducing ViPC (view-guided point cloud completion) that takes the missing crucial global structure information from an extra single-view image by leveraging a framework that sequentially performs effective cross-modality and cross-level fusions.

Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding

This paper proposes two simultaneous cycle transformations between the latent spaces of complete shapes and incomplete ones, and experimentally shows that the model with the learned bidirectional geometry correspondence outperforms state-of-the-art unpaired completion methods.



Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network

This work introduces DensePCR, a deep pyramidal network for point cloud reconstruction that hierarchically predicts point clouds of increasing resolution, and proposes an architecture that first predicts a low-resolution point cloud, and then hierarchically increases the resolution by aggregating local and global point features to deform a grid.

Morphing and Sampling Network for Dense Point Cloud Completion

This work proposes a novel approach to complete the partial point cloud in two stages, which outperforms the existing methods in both the Earth Mover's Distance (EMD) and the Chamfer Distance (CD).

PointConv: Deep Convolutional Networks on 3D Point Clouds

The dynamic filter is extended to a new convolution operation, named PointConv, which can be applied on point clouds to build deep convolutional networks and is able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds.

PCN: Point Completion Network

The experiments show that PCN produces dense, complete point clouds with realistic structures in the missing regions on inputs with various levels of incompleteness and noise, including cars from LiDAR scans in the KITTI dataset.

Interpolated Convolutional Networks for 3D Point Cloud Understanding

A novel Interpolated Convolution operation, InterpConv, is proposed to tackle the point cloud feature learning and understanding problem, to utilize a set of discrete kernel weights and interpolate point features to neighboring kernel-weight coordinates by an interpolation function for convolution.

TopNet: Structural Point Cloud Decoder

This work proposes a novel decoder that generates a structured point cloud without assuming any specific structure or topology on the underlying point set, and significantly outperforms state-of-the-art 3D point cloud completion methods on the Shapenet dataset.

Dynamic Graph CNN for Learning on Point Clouds

This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

A novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds, and is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid.

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

  • Hang SuV. Jampani J. Kautz
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
A network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice that outperforms existing state-of-the-art techniques on 3D segmentation tasks.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.