DeepAI AI Chat
Log In Sign Up

IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment

by   Yiming Zeng, et al.
City University of Hong Kong

This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) and further reason that temporal irregularity and under-sampling are two major challenges. To tackle the challenges, we propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. Specifically, we propose a temporal consistency learning module to align two consecutive point cloud frames point-wisely, based on which we can employ linear interpolation to obtain coarse trajectories/in-between frames. To compensate the high-order nonlinear components of trajectories, we apply aligned feature embeddings that encode local geometry properties to regress point-wise increments, which are combined with the coarse estimations. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually. Our framework can bring benefits to 3D motion data acquisition. The source code is publicly available at


page 7

page 12

page 13

page 14


PointINet: Point Cloud Frame Interpolation Network

LiDAR point cloud streams are usually sparse in time dimension, which is...

ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation

Recent works of point clouds show that mulit-frame spatio-temporal model...

VoxelContext-Net: An Octree based Framework for Point Cloud Compression

In this paper, we propose a two-stage deep learning framework called Vox...

D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction

The non-uniformly distributed nature of the 3D dynamic point cloud (DPC)...

Deep Magnification-Arbitrary Upsampling over 3D Point Clouds

This paper addresses the problem of generating dense point clouds from g...

Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis

Point clouds are characterized by irregularity and unstructuredness, whi...

FloorPP-Net: Reconstructing Floor Plans using Point Pillars for Scan-to-BIM

This paper presents a deep learning-based point cloud processing method ...