REVIEW 7 cited by
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
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.
Forward citations
Cited by 7 Pith papers
-
BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning
A contrastive learning framework with instance-level and perspective-level losses consistently improves multiple BEV detection models on nuScenes by up to 2.4 mAP.
-
NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and Collaboration
NoiseController decomposes initial diffusion noise into scene-level foreground/background and shared/residual components, then collaborates them across views and frames, improving multi-view video consistency on nuScenes.
-
Distant Object Localisation from Noisy Image Segmentation Sequences
A bootstrap particle filter localizes distant static objects in 3D from noisy image segmentation sequences and GNSS camera poses, shown in simulation and one real drone sequence.
-
Achieving Precise and Reliable Locomotion with Differentiable Simulation-Based System Identification
Estimating robot dynamics parameters from trajectory data alone inside a differentiable simulator, inside the reinforcement learning loop, is claimed to improve trajectory following in bipedal locomotion.
-
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
A humanoid-specific multimodal occupancy perception system with a new dataset, sensor layout, and a fusion network that claims state-of-the-art results on its own benchmark.
-
Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model
A reactive closed-loop driving simulator that uses a diffusion renderer with retrieval from real recordings, plus a nuPlan behavioral controller, to generate sensor images in response to an end-to-end driving model's actions.
-
CrossTracker: Robust Multi-modal 3D Multi-Object Tracking via Cross Correction
A two-stage camera-LiDAR 3D tracker that generates coarse dual-stream trajectories and then refines them via cross-modal correction, achieving state-of-the-art KITTI results.
Discussion (0). Continue with ORCID to comment.