DeepAI AI Chat
Log In Sign Up

Dynamic 3D Scene Analysis by Point Cloud Accumulation

by   Shengyu Huang, et al.

Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robots, acquire sequences of 3D range scans ("frames"). Each frame covers the scene sparsely, due to limited angular scanning resolution and occlusion. The sparsity restricts the performance of downstream processes like semantic segmentation or surface reconstruction. Luckily, when the sensor moves, frames are captured from a sequence of different viewpoints. This provides complementary information and, when accumulated in a common scene coordinate frame, yields a denser sampling and a more complete coverage of the underlying 3D scene. However, often the scanned scenes contain moving objects. Points on those objects are not correctly aligned by just undoing the scanner's ego-motion. In the present paper, we explore multi-frame point cloud accumulation as a mid-level representation of 3D scan sequences, and develop a method that exploits inductive biases of outdoor street scenes, including their geometric layout and object-level rigidity. Compared to state-of-the-art scene flow estimators, our proposed approach aims to align all 3D points in a common reference frame correctly accumulating the points on the individual objects. Our approach greatly reduces the alignment errors on several benchmark datasets. Moreover, the accumulated point clouds benefit high-level tasks like surface reconstruction.


page 26

page 27


PointINet: Point Cloud Frame Interpolation Network

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

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception

State-of-the-art methods for driving-scene LiDAR-based perception (inclu...

Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene Flow

Low-resolution point clouds are challenging for object detection methods...

Efficient moving point handling for incremental 3D manifold reconstruction

As incremental Structure from Motion algorithms become effective, a good...

Scalable Scene Flow from Point Clouds in the Real World

Autonomous vehicles operate in highly dynamic environments necessitating...

LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment

Understanding and interpreting a 3d environment is a key challenge for a...

DNN Filter for Bias Reduction in Distribution-to-Distribution Scan Matching

Distribution-to-distribution (D2D) point cloud registration techniques s...