Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds

by   Kosuke Arase, et al.

Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots. Certain existing studies have split input point clouds into small regions such as 1m x 1m; one reason for this is that models in the studies cannot consume a large number of points because of the large space complexity. However, because such small regions occasionally include a very small number of instances belonging to the same class, an evaluation using existing metrics such as mAP is largely affected by the category recognition performance. To address these problems, we propose a new method with space complexity O(Np) such that large regions can be consumed, as well as novel metrics for tasks that are independent of the categories or size of the inputs. Our method learns a mapping from input point clouds to an embedding space, where the embeddings form clusters for each instance and distinguish instances using these clusters during testing. Our method achieves state-of-the-art performance using both existing and the proposed metrics. Moreover, we show that our new metric can evaluate the performance of a task without being affected by any other condition.


Learning Gaussian Instance Segmentation in Point Clouds

This paper presents a novel method for instance segmentation of 3D point...

NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds

We introduce a method for instance proposal generation for 3D point clou...

Learning Stixel-based Instance Segmentation

Stixels have been successfully applied to a wide range of vision tasks i...

Identifying Unknown Instances for Autonomous Driving

In the past few years, we have seen great progress in perception algorit...

ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation

Separating 3D point clouds into individual instances is an important tas...

Exploring Cross-Point Embeddings for 3D Dense Uncertainty Estimation

Dense prediction tasks are common for 3D point clouds, but the inherent ...

Please sign up or login with your details

Forgot password? Click here to reset