PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation

11/29/2017
by   Danfei Xu, et al.
0

We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multi-stage pipelines or hold sensor and dataset-specific assumptions, PointFusion is conceptually simple and application-agnostic. The image data and the raw point cloud data are independently processed by a CNN and a PointNet architecture, respectively. The resulting outputs are then combined by a novel fusion network, which predicts multiple 3D box hypotheses and their confidences, using the input 3D points as spatial anchors. We evaluate PointFusion on two distinctive datasets: the KITTI dataset that features driving scenes captured with a lidar-camera setup, and the SUN-RGBD dataset that captures indoor environments with RGB-D cameras. Our model is the first one that is able to perform better or on-par with the state-of-the-art on these diverse datasets without any dataset-specific model tuning.

READ FULL TEXT

page 1

page 3

page 6

page 8

research
04/25/2021

Temp-Frustum Net: 3D Object Detection with Temporal Fusion

3D object detection is a core component of automated driving systems. St...
research
04/21/2020

YOLO and K-Means Based 3D Object Detection Method on Image and Point Cloud

Lidar based 3D object detection and classification tasks are essential f...
research
05/08/2020

View Invariant Human Body Detection and Pose Estimation from Multiple Depth Sensors

Point cloud based methods have produced promising results in areas such ...
research
11/22/2019

PointPainting: Sequential Fusion for 3D Object Detection

Camera and lidar are important sensor modalities for robotics in general...
research
09/21/2023

2DDATA: 2D Detection Annotations Transmittable Aggregation for Semantic Segmentation on Point Cloud

Recently, multi-modality models have been introduced because of the comp...
research
03/19/2019

Geometry-constrained Car Recognition Using a 3D Perspective Network

We present a novel learning framework for vehicle recognition from a sin...
research
03/15/2021

3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks

In this work we propose 3D-FFS, a novel approach to make sensor fusion b...

Please sign up or login with your details

Forgot password? Click here to reset