Skip to content
AI News HubLIVE
Original source2 min read

BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving

Summary

BEVCast introduces a two-stage bird's-eye-view representation whose resolution adapts to the predicted driving path: a coarse 4.096 m grid encodes the whole scene, and only the highest-heat cells are refined to 1.024 m under a fixed budget, cutting BEV encoder time to 66% while improving accuracy on nuScenes and NAVSIM.

SourcearXiv Computer VisionAuthor: Qiren Wang, Mingyu Guo, Zixuan Wang, Weisong Shi
BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 5 Nov 2026]

Title:BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving

View a PDF of the paper titled BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving, by Qiren Wang and 3 other authors

View PDF HTML (experimental)

Abstract:Camera-based driving models build a dense bird's-eye-view (BEV) grid and spend the same computation on every cell of it, although the vehicle crosses only a few of those cells within the planning horizon. We present BEVCast, a two-stage BEV whose resolution adapts to the predicted driving path. A coarse pass encodes the whole scene on a grid of 4.096 m cells. A heat head trained on the recorded path assigns a heat to every coarse cell and the cells with the highest heat are refined into 1.024 m cells under a fixed budget. The remaining cells keep their coarse resolution, so the trajectory head reads a mixed-resolution BEV that still covers the entire scene and needs neither an HD map nor a navigation command. Against a full grid of 1.024 m cells with the same architecture and training recipe, BEVCast at a 10% refinement budget encodes 28% of the BEV queries and needs 66% of the BEV encoder time at batch size 1. On nuScenes its mean displacement error is 1.078 m against 1.149 m and its drivable area violation rate is 1.46% against 2.29%. On NAVSIM navtest its mean displacement error is 0.577 m against 0.598 m and its extended predictive driver model score is 82.51 against 81.28. Next to published planners BEVCast reaches a comparable error on both benchmarks without a navigation command. The resolution of a driving BEV can therefore follow the task instead of the grid.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.08631 [cs.CV]

(or arXiv:2611.08631v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.08631

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qiren Wang [view email] [v1] Thu, 5 Nov 2026 19:27:01 UTC (4,874 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled BEVCast: Path-Adaptive BEV for Efficient End-to-End Autonomous Driving, by Qiren Wang and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Two-stage BEV: a coarse grid covers the full scene while only high-heat cells are refined.
  • At a 10% refinement budget it encodes 28% of BEV queries and needs 66% of encoder time at batch size 1.
  • nuScenes mean displacement error is 1.078 m vs. 1.149 m, with drivable area violations at 1.46% vs. 2.29%.
  • It needs neither an HD map nor a navigation command and matches published planners on NAVSIM navtest.

Highlights and analysis are generated automatically and may contain errors. Check the original source.