REVIEW 3 cited by
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
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
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
read the original abstract
In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilizes the temporal information of previous frames to boost 3D object detection. More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling. The 3D PE achieves the temporal alignment on object position of different frames. A feature-guided position encoder is further introduced to improve the data adaptability of 3D PE. To support for multi-task learning (e.g., BEV segmentation and 3D lane detection), PETRv2 provides a simple yet effective solution by introducing task-specific queries, which are initialized under different spaces. PETRv2 achieves state-of-the-art performance on 3D object detection, BEV segmentation and 3D lane detection. Detailed robustness analysis is also conducted on PETR framework. We hope PETRv2 can serve as a strong baseline for 3D perception. Code is available at \url{https://github.com/megvii-research/PETR}.
Forward citations
Cited by 3 Pith papers
-
Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification in Physics Simulation
First application of split conformal prediction to neural operators, providing distribution-free intervals with 89.1% empirical coverage on heat conduction benchmarks and an adaptive normalized variant using MC Dropout.
-
A Resource Efficient Fusion Network for Object Detection in Bird's-Eye View using Camera and Raw Radar Data
Describes a camera-radar fusion network that uses raw RD spectra and BEV-polar camera features for BEV object detection, evaluated for accuracy and compute on the RADIal dataset.
-
Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
A survey that organizes Transformer-based autonomous driving models by task and architecture while analyzing compression techniques as a system-level deployment concern.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.