RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection

[2505.17732] RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2505.17732 (cs) [Submitted on 23 May 2025 ( v1 ), last revised 8 Apr 2026 (this version, v2)] Title: RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection Authors: Ozsel Kilinc , Cem Tarhan View a PDF of the paper titled RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection, by Ozsel Kilinc and 1 other authors View PDF HTML (experimental) Abstract: Accurate, fast, and reliable 3D perception is essential for autonomous driving. Recently, bird's-eye view (BEV)-based perception approaches have emerged as superior alternatives to perspective-based solutions, offering enhanced spatial understanding and more natural outputs for planning. Existing BEV-based 3D object detection methods, typically using an angle-based representation, directly estimate the size and orientation of rotated bounding boxes. We observe that BEV-based 3D object detection is analogous to aerial oriented object detection, where angle-based methods are known to suffer from discontinuities in their loss functions. Drawing inspiration from this domain, we propose \textbf{R}estricted \textbf{Q}uadrilateral \textbf{R}epresentation to define \textbf{3D} regression targets. RQR3D regresses the smallest horizontal bounding box encapsulating the oriented box, along with the offsets between the corners of these two boxes, thereby transforming the oriented object detection problem into a keypoint regression task. We employ RQR3D within an anchor-free single-stage object detection method achieving state-of-the-art performance. We show that the proposed architecture is compatible with different object detection approaches. Furthermore, we introduce a simplified radar fusion backbone that applies standard 2D convolutions to radar features. This backbone leverages the inherent 2D structure of the data for efficient and geometrically consistent processing without over-parameterization, thereby eliminating the need for voxel grouping and sparse convolutions. Extensive evaluations on the nuScenes dataset show that RQR3D achieves SotA camera-radar 3D object detection performance despite its lightweight design, reaching 67.5 NDS and 59.7 mAP with reduced translation and orientation errors, which are crucial for safe autonomous driving. Comments: To appear in proceedings of CVPR Findings 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2505.17732 [cs.CV] (or arXiv:2505.17732v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2505.17732 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ozsel Kilinc [ view email ] [v1] Fri, 23 May 2025 10:52:34 UTC (3,940 KB) [v2] Wed, 8 Apr 2026 21:19:36 UTC (724 KB) Full-text links: Access Paper: View a PDF of the paper titled RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection, by Ozsel Kilinc and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-05 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• OneCanvas: 3D Scene Understanding via Panoramic Reprojection#1118611
• MFR-YOLO: advancing UAV object detection with multi-scale feature refinement via deformable convolution and global attention.#214302
• Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models#821978
• NaCR: Visual Localization via NeRF-aided Camera Ray Regression#1061814
• PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipeline#1037370