# BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection

Source: [BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection](<https://www.sota2.com/research/paper/68fa72a31e209131cea57b88>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:30:51.475Z

Authors: Zhenxin Li, Shiyi Lan, Jose M. Alvarez, Zuxuan Wu

Published: 2023-12-04T07:35:02.000Z

## Abstract

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their outstanding abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set. Code will be available at \\url{https://github.com/woxihuanjiangguo/BEVNeXt}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Object Detection on nuScenes (val) (Core Metrics)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-val-core-metrics.md>): 3D Object Detection; nuScenes (val); NDS: 54.8.

- [3D Object Detection on nuScenes (val)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-val.md>): 3D Object Detection; nuScenes (val); NDS: 59.7.

- [3D Object Detection on nuScenes (test)](<https://www.sota2.com/research/sota/3d-object-detection-on-nuscenes-test.md>): 3D Object Detection; nuScenes (test); mAP: 55.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.01696>)

[PDF](<https://arxiv.org/pdf/2312.01696.pdf>)