Saved in:
Bibliographic Details
Main Authors: Wu, Di, Yang, Feng, Zhao, Wenhui, Yu, Jinwen, Liao, Pan, Xu, Benlian, Zhang, Dingwen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17620
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917157342806016
author Wu, Di
Yang, Feng
Zhao, Wenhui
Yu, Jinwen
Liao, Pan
Xu, Benlian
Zhang, Dingwen
author_facet Wu, Di
Yang, Feng
Zhao, Wenhui
Yu, Jinwen
Liao, Pan
Xu, Benlian
Zhang, Dingwen
contents Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate object-relevant features from multi-view images through a set of learnable queries, offering a concise and end-to-end detection paradigm. Building on this foundation, MV2D leverages 2D detection results to provide high-quality object priors for query initialization, enabling higher precision and recall. However, the inherent depth ambiguity in single-frame 2D detections still limits the accuracy of 3D query generation. To address this issue, we propose StereoMV2D, a unified framework that integrates temporal stereo modeling into the 2D detection-guided multi-view 3D detector. By exploiting cross-temporal disparities of the same object across adjacent frames, StereoMV2D enhances depth perception and refines the query priors, while performing all computations efficiently within 2D regions of interest (RoIs). Furthermore, a dynamic confidence gating mechanism adaptively evaluates the reliability of temporal stereo cues through learning statistical patterns derived from the inter-frame matching matrix together with appearance consistency, ensuring robust detection under object appearance and occlusion. Extensive experiments on the nuScenes and Argoverse 2 datasets demonstrate that StereoMV2D achieves superior detection performance without incurring significant computational overhead. Code will be available at https://github.com/Uddd821/StereoMV2D.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StereoMV2D: A Sparse Temporal Stereo-Enhanced Framework for Robust Multi-View 3D Object Detection
Wu, Di
Yang, Feng
Zhao, Wenhui
Yu, Jinwen
Liao, Pan
Xu, Benlian
Zhang, Dingwen
Computer Vision and Pattern Recognition
Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate object-relevant features from multi-view images through a set of learnable queries, offering a concise and end-to-end detection paradigm. Building on this foundation, MV2D leverages 2D detection results to provide high-quality object priors for query initialization, enabling higher precision and recall. However, the inherent depth ambiguity in single-frame 2D detections still limits the accuracy of 3D query generation. To address this issue, we propose StereoMV2D, a unified framework that integrates temporal stereo modeling into the 2D detection-guided multi-view 3D detector. By exploiting cross-temporal disparities of the same object across adjacent frames, StereoMV2D enhances depth perception and refines the query priors, while performing all computations efficiently within 2D regions of interest (RoIs). Furthermore, a dynamic confidence gating mechanism adaptively evaluates the reliability of temporal stereo cues through learning statistical patterns derived from the inter-frame matching matrix together with appearance consistency, ensuring robust detection under object appearance and occlusion. Extensive experiments on the nuScenes and Argoverse 2 datasets demonstrate that StereoMV2D achieves superior detection performance without incurring significant computational overhead. Code will be available at https://github.com/Uddd821/StereoMV2D.
title StereoMV2D: A Sparse Temporal Stereo-Enhanced Framework for Robust Multi-View 3D Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.17620