Saved in:
Bibliographic Details
Main Authors: Liao, Pan, Yang, Feng, Wu, Di, Zhao, Wenhui, Yu, Jinwen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.15176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929606077972480
author Liao, Pan
Yang, Feng
Wu, Di
Zhao, Wenhui
Yu, Jinwen
author_facet Liao, Pan
Yang, Feng
Wu, Di
Zhao, Wenhui
Yu, Jinwen
contents Monocular 3D object detection has vast application potential across various fields. DETR-type models have shown remarkable performance in different areas, but there is still considerable room for improvement in monocular 3D detection, especially with the existing DETR-based method, MonoDETR. After addressing the query initialization issues in MonoDETR, we explored several performance enhancement strategies, such as incorporating a more efficient encoder and utilizing a more powerful depth estimator. Ultimately, we proposed MonoDETRNext, a model that comes in two variants based on the choice of depth estimator: MonoDETRNext-E, which prioritizes speed, and MonoDETRNext-A, which focuses on accuracy. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 3.52$\%$ improvement in the $AP_{3D}$ metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-E showed a 2.35$\%$ increase. Additionally, the computational efficiency of MonoDETRNext-E slightly exceeds that of its predecessor.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15176
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector
Liao, Pan
Yang, Feng
Wu, Di
Zhao, Wenhui
Yu, Jinwen
Computer Vision and Pattern Recognition
Monocular 3D object detection has vast application potential across various fields. DETR-type models have shown remarkable performance in different areas, but there is still considerable room for improvement in monocular 3D detection, especially with the existing DETR-based method, MonoDETR. After addressing the query initialization issues in MonoDETR, we explored several performance enhancement strategies, such as incorporating a more efficient encoder and utilizing a more powerful depth estimator. Ultimately, we proposed MonoDETRNext, a model that comes in two variants based on the choice of depth estimator: MonoDETRNext-E, which prioritizes speed, and MonoDETRNext-A, which focuses on accuracy. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 3.52$\%$ improvement in the $AP_{3D}$ metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-E showed a 2.35$\%$ increase. Additionally, the computational efficiency of MonoDETRNext-E slightly exceeds that of its predecessor.
title MonoDETRNext: Next-Generation Accurate and Efficient Monocular 3D Object Detector
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.15176