KT-Net: Knowledge Transfer for Unpaired 3D Shape Completion (2021-11-23T00:00:00.000000Z)

TL;DR

The novel KTNet elaborates a teacher-assistant-student network to establish multiple knowledge transfer processes to establish the geometric correspondence between complete and incomplete shapes in a perspective of knowledge transfer, which enables more detailed geometric inference for generating high-quality complete shapes.

Abstract

Unpaired 3D object completion aims to predict a complete 3D shape from an incomplete input without knowing the correspondence between the complete and incomplete shapes. In this paper, we propose the novel KTNet to solve this task from the new perspective of knowledge transfer. KTNet elaborates a teacher-assistant-student network to establish multiple knowledge transfer processes. Specifically, the teacher network takes complete shape as input and learns the knowledge of complete shape. The student network takes the incomplete one as input and restores the corresponding complete shape. And the assistant modules not only help to transfer the knowledge of complete shape from the teacher to the student, but also judge the learning effect of the student network. As a result, KTNet makes use of a more comprehensive understanding to establish the geometric correspondence between complete and incomplete shapes in a perspective of knowledge transfer, which enables more detailed geometric inference for generating high-quality complete shapes. We conduct comprehensive experiments on several datasets, and the results show that our method outperforms previous methods of unpaired point cloud completion by a large margin. Code is available at https://github.com/a4152684/KT-Net.

Authors

Bisheng Yang

2 papers

Wenxiao Zhang

2 papers

Xin Wen

2 papers

TL;DR

Abstract

Authors

References62 items

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints

Learning Local Displacements for Point Cloud Completion

Learning a Structured Latent Space for Unsupervised Point Cloud Completion

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

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

Extending 6-DoF VR Experience Via Multi-Sphere Images Interpolation

MM-Flow: Multi-modal Flow Network for Point Cloud Completion

RFNet: Recurrent Forward Network for Dense Point Cloud Completion

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

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

Voxel-based Network for Shape Completion by Leveraging Edge Generation

PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

ME-PCN: Point Completion Conditioned on Mask Emptiness

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

Unsupervised 3D Shape Completion through GAN Inversion

Variational Relational Point Completion Network

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

Denoise and Contrast for Category Agnostic Shape Completion

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

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

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

ChartPointFlow for Topology-Aware 3D Point Cloud Generation

Vaccine-style-net: Point Cloud Completion in Implicit Continuous Function Space

KAPLAN: A 3D Point Descriptor for Shape Completion

Detail Preserved Point Cloud Completion via Separated Feature Aggregation

GRNet: Gridding Residual Network for Dense Point Cloud Completion

Point Cloud Completion by Skip-Attention Network With Hierarchical Folding

Cascaded Refinement Network for Point Cloud Completion

Multimodal Shape Completion via Conditional Generative Adversarial Networks

PF-Net: Point Fractal Network for 3D Point Cloud Completion

Morphing and Sampling Network for Dense Point Cloud Completion

Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction

TopNet: Structural Point Cloud Decoder

Deep Closest Point: Learning Representations for Point Cloud Registration

Unpaired Point Cloud Completion on Real Scans using Adversarial Training

Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpainting

PCN: Point Completion Network

Learning 3D Shape Completion from Laser Scan Data with Weak Supervision

A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving

Dynamic Graph CNN for Learning on Point Clouds

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation

Shape Inpainting Using 3D Generative Adversarial Network and Recurrent Convolutional Networks

Matterport3D: Learning from RGB-D Data in Indoor Environments

3D Object Reconstruction from a Single Depth View with Adversarial Learning

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes

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

Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis

Robotic Online Path Planning on Point Cloud

ShapeNet: An Information-Rich 3D Model Repository

Aligning 3D models to RGB-D images of cluttered scenes

Database‐Assisted Object Retrieval for Real‐Time 3D Reconstruction

Distilling the Knowledge in a Neural Network

Are we ready for autonomous driving? The KITTI vision benchmark suite

Bottom-Up/Top-Down Image Parsing with Attribute Grammar

Partial and approximate symmetry detection for 3D geometry

Filling holes in complex surfaces using volumetric diffusion

Visualizing Data using t-SNE

SEGMENTATION OF POINT CLOUDS USING SMOOTHNESS CONSTRAINT

Field of Study

Venue Information

Name

Type

URL

Alternate Names