Saved in:
Bibliographic Details
Main Authors: Gupta, Pranav, Rengarajan, Rishabh, Bankapur, Viren, Mannem, Vedansh, Ahuja, Lakshit, Vijay, Surya, Wang, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.11211
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913548059279360
author Gupta, Pranav
Rengarajan, Rishabh
Bankapur, Viren
Mannem, Vedansh
Ahuja, Lakshit
Vijay, Surya
Wang, Kevin
author_facet Gupta, Pranav
Rengarajan, Rishabh
Bankapur, Viren
Mannem, Vedansh
Ahuja, Lakshit
Vijay, Surya
Wang, Kevin
contents Combining LiDAR and Camera-view data has become a common approach for 3D Object Detection. However, previous approaches combine the two input streams at a point-level, throwing away semantic information derived from camera features. In this paper we propose Cross-View Center Point-Fusion, a state-of-the-art model to perform 3D object detection by combining camera and LiDAR-derived features in the BEV space to preserve semantic density from the camera stream while incorporating spacial data from the LiDAR stream. Our architecture utilizes aspects from previously established algorithms, Cross-View Transformers and CenterPoint, and runs their backbones in parallel, allowing efficient computation for real-time processing and application. In this paper we find that while an implicitly calculated depth-estimate may be sufficiently accurate in a 2D map-view representation, explicitly calculated geometric and spacial information is needed for precise bounding box prediction in the 3D world-view space.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11211
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Prediction
Gupta, Pranav
Rengarajan, Rishabh
Bankapur, Viren
Mannem, Vedansh
Ahuja, Lakshit
Vijay, Surya
Wang, Kevin
Computer Vision and Pattern Recognition
Machine Learning
Combining LiDAR and Camera-view data has become a common approach for 3D Object Detection. However, previous approaches combine the two input streams at a point-level, throwing away semantic information derived from camera features. In this paper we propose Cross-View Center Point-Fusion, a state-of-the-art model to perform 3D object detection by combining camera and LiDAR-derived features in the BEV space to preserve semantic density from the camera stream while incorporating spacial data from the LiDAR stream. Our architecture utilizes aspects from previously established algorithms, Cross-View Transformers and CenterPoint, and runs their backbones in parallel, allowing efficient computation for real-time processing and application. In this paper we find that while an implicitly calculated depth-estimate may be sufficiently accurate in a 2D map-view representation, explicitly calculated geometric and spacial information is needed for precise bounding box prediction in the 3D world-view space.
title CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Prediction
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2410.11211