mlsanityData to 7 Oct 2026

RoPETR: Improving Temporal Camera-Only 3D Detection by Integrating Enhanced Rotary Position Embedding

arXiv 2504.12643 ↗First posted 17 Apr 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

This technical report introduces a targeted improvement to the StreamPETR framework, specifically aimed at enhancing velocity estimation, a critical factor influencing the overall NuScenes Detection Score. While StreamPETR exhibits strong 3D bounding box detection performance as reflected by its high mean Average Precision our analysis identified velocity estimation as a substantial bottleneck when evaluated on the NuScenes dataset. To overcome this limitation, we propose a customized positional embedding strategy tailored to enhance temporal modeling capabilities. Experimental evaluations conducted on the NuScenes test set demonstrate that our improved approach achieves a state-of-the-art NDS of 70.86% using the ViT-L backbone, setting a new benchmark for camera-only 3D object detection.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 30 of its 34 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

30 of 34 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Mask R-CNNcited by 7,259
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  10. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  11. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  12. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
18 more
  1. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  2. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  3. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  4. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  5. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  6. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  7. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  8. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  9. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  10. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  11. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  12. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  13. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  14. 2022HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigationcited by 69
  15. 2023Sparse4D v3: Advancing End-to-End 3D Detection and Trackingcited by 69
  16. 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detectioncited by 39
  17. 2023Object as Query: Lifting any 2D Object Detector to 3D Detectioncited by 38
  18. 2024Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detectioncited by 36

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perceptioncited by 3
  2. 2026SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMscited by 2
  3. 2026nD-RoPE: A Generalized RoPE for n-Dimensional Position Embeddingcited by 2
  4. 2026Geometry-Grounded Unified 3D Perception for Autonomous Drivingcited by 2
  5. 2025PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Taskscited by 1
  6. 2026Information Coordination as a Bridge: A Neuro-Symbolic Architecture for Reliable Autonomous Driving Scene Understandingcited by 0
  7. 2026PQR3D: Progressive Query Refinement over Reference-Conditioned Temporal Windows for Multi-View 3D Object Detectioncited by 0