Papers › Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection

21 Mar 2023ICCV 2023 1arXiv:2303.11926archive 2025-07-28

Shihao Wang, Yingfei Liu, Tiancai Wang, Ying Li, Xiangyu Zhang

In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The model is performed in an online manner and the long-term historical information is propagated through object queries frame by frame. Besides, we introduce a motion-aware layer normalization to model the movement of the objects. StreamPETR achieves significant performance improvements only with negligible computation cost, compared to the single-frame baseline. On the standard nuScenes benchmark, it is the first online multi-view method that achieves comparable performance (67.6% NDS & 65.3% AMOTA) with lidar-based methods. The lightweight version realizes 45.0% mAP and 31.7 FPS, outperforming the state-of-the-art method (SOLOFusion) by 2.3% mAP and 1.8x faster FPS. Code has been available at https://github.com/exiawsh/StreamPETR.git.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

exiawsh/streampetr officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
wenyuqing/panacea mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Panacea: Panoramic and Controllable Video Generation for Autonomous Driving (arXiv:2311.16813; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Multi-Object Tracking3D Object DetectionObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Multi-Object Tracking nuScenes Camera Only StreamPETR-Large AMOTA 65.3 #1 of 1 Archive leaderboard report
3D Object Detection 3D Object Detection on Argoverse2 Camera Only StreamPETR Average mAP 20.3 #2 of 3 Archive leaderboard report
3D Object Detection nuScenes Camera Only StreamPETR-Large Future Frame false #4 of 19 Archive leaderboard report
3D Object Detection nuScenes Camera Only StreamPETR-Large NDS 67.6 #4 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Layer Normalization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections