PointCaM: Cut-and-Mix for Open-Set Point Cloud Analysis

12/05/2022
by   Jie Hong, et al.
0

Point cloud analysis is receiving increasing attention, however, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper mainly discusses point cloud analysis under open-set settings, where we train the model without data from unknown classes and identify them in the inference stage. Basically, we propose to solve open-set point cloud analysis using a novel Point Cut-and-Mix mechanism consisting of Unknown-Point Simulator and Unknown-Point Estimator modules. Specifically, we use the Unknown-Point Simulator to simulate unknown data in the training stage by manipulating the geometric context of partial known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context for discriminating the known and unknown data. Extensive experiments show the plausibility of open-set point cloud analysis and the effectiveness of our proposed solutions. Our code is available at <https://github.com/ShiQiu0419/pointcam>.

READ FULL TEXT
research
05/02/2023

PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling

Despite the recent development of deep learning-based point cloud upsamp...
research
08/02/2021

Investigating Attention Mechanism in 3D Point Cloud Object Detection

Object detection in three-dimensional (3D) space attracts much interest ...
research
03/25/2023

VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud

The task of 3D semantic scene graph (3DSSG) prediction in the point clou...
research
10/30/2022

Interpretable Geometric Deep Learning via Learnable Randomness Injection

Point cloud data is ubiquitous in scientific fields. Recently, geometric...
research
11/14/2020

Planning Paths Through Unknown Space by Imagining What Lies Therein

This paper presents a novel framework for planning paths in maps contain...
research
03/28/2022

Equivariant Point Cloud Analysis via Learning Orientations for Message Passing

Equivariance has been a long-standing concern in various fields ranging ...
research
12/05/2022

Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities

Downsampling and feature extraction are essential procedures for 3D poin...

Please sign up or login with your details

Forgot password? Click here to reset