• Corpus ID: 244920632

A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion

  title={A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion},
  author={Zhaoyang Lyu and Zhifeng Kong and Xudong Xu and Liang Pan and Dahua Lin},
3D point cloud is an important 3D representation for capturing real world 3D objects. However, real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. The CD loss estimates correspondences between two point clouds by searching nearest neighbors, which does not capture the overall point density distribution on the generated shape… 

Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results

Methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration are reported, and the top-ranked solutions will be analyzed and the future research directions are discussed.

Multi-Scope Feature Extraction for Point Cloud Completion

This work proposes a multi-scope feature extraction method in the encoder, where multiple k-nearest neighbors are considered in the edge convolution and integrates the original partial point cloud in the decoder to maintain the given geometric shape information.

LION: Latent Point Diffusion Models for 3D Shape Generation

The hierarchical Latent Point Diffusion Model (LION) is introduced, set up as a variational autoencoder (VAE) with a hierarchical latent space that combines a global shape latent representation with a point-structured latent space for 3D shape generation.

Fast Point Cloud Generation with Straight Flows

This work proposes Point Straight Flow (PSF), a model that exhibits impressive performance using one step, based on the reformulation of the standard diffusion model, which optimizes the curvy learning trajectory into a straight path, enabling applications to 3D real-world with latency constraints.

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

This work aims to conduct a comprehensive survey on various methods of point cloud completion, including point-based, view- based, convolution-based), convolution, graph, graph based, generative model based, transformer-based approaches, etc, and summarizes the comparisons among these methods to provoke further research insights.

Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation

This study proposes the Diffusion Unit (DU) that handles edges in an interpretable manner while providing decent improvement, and achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentsation using S3DIS.

KTNet: Knowledge Transfer for Unpaired 3D Shape Completion

This paper proposes the novel KT-Net, which elaborates a teacher-assistant-student network to establish multiple knowledge transfer processes and makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes in a perspective of knowledge transfer.

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

Diffusion models have emerged as the new state-of-the-art generative model with high quality samples, with intriguing properties such as mode coverage and high flexibil-ity. They have also been shown

HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising

A novel approach for vector-floorplan generation via a diffusion model, which denoises 2D coordinates of room/door corners with two inference ob-jectives, which makes significant improvements in all the metrics against the state-of-the-art with significant margins.

Few-shot Image Generation with Diffusion Models

This paper makes the first attempt to study when do DDPMs overfit and suffer severe diversity degradation as training data become scarce and proposes a DDPM-based pairwise similarity loss to preserve the relative distances between generated samples during domain adaptation.



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).

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.

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.

GRNet: Gridding Residual Network for Dense Point Cloud Completion

This work devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information, and presents the differentiable Cubic Feature Sampling layer to extract features of neighboring points, which preserves context information.

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.

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.

Detail Preserved Point Cloud Completion via Separated Feature Aggregation

Qualitative and quantitative evaluations demonstrate that the proposed network outperforms current state-of-the art methods especially on detail preservation.

3D Shape Generation and Completion through Point-Voxel Diffusion

Point-Voxel Diffusion is a unified, probabilistic formulation for unconditional shape generation and conditional, multi-modal shape completion that marries denoising diffusion models with the hybrid, pointvoxel representation of 3D shapes.

ECG: Edge-aware Point Cloud Completion with Graph Convolution

  • Liang Pan
  • Computer Science
    IEEE Robotics and Automation Letters
  • 2020
The proposed ECG - an Edge-aware point cloud Completion network with Graph convolution, which facilitates fine-grained 3D point cloud shape generation with multi-scale edge features, significantly outperforms previous state-of-the-art (SOTA) methods for point cloud completion.

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.