GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection

• URL: http://arxiv.org/abs/2409.01816v1
• Date: Tue, 3 Sep 2024 11:57:36 GMT
• Title: GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection
• Authors: Jinqing Zhang, Yanan Zhang, Yunlong Qi, Zehua Fu, Qingjie Liu, Yunhong Wang,
• Abstract summary: Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection. Existing methods overlook the geometric quality of BEV representation, leaving it in a low-resolution state.
• Score: 36.245654685143016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation, leaving it in a low-resolution state and failing to restore the authentic geometric information of the scene. In this paper, we identify the reasons why previous approaches are constrained by low BEV representation resolution and propose Radial-Cartesian BEV Sampling (RC-Sampling), enabling efficient generation of high-resolution dense BEV representations without the need for complex operators. Additionally, we design a novel In-Box Label to substitute the traditional depth label generated from the LiDAR points. This label reflects the actual geometric structure of objects rather than just their surfaces, injecting real-world geometric information into the BEV representation. Furthermore, in conjunction with the In-Box Label, a Centroid-Aware Inner Loss (CAI Loss) is developed to capture the fine-grained inner geometric structure of objects. Finally, we integrate the aforementioned modules into a novel multi-view 3D object detection framework, dubbed GeoBEV. Extensive experiments on the nuScenes dataset exhibit that GeoBEV achieves state-of-the-art performance, highlighting its effectiveness.

Related papers

• Towards Unified 3D Object Detection via Algorithm and Data Unification [70.27631528933482]
  We build the first unified multi-modal 3D object detection benchmark MM- Omni3D and extend the aforementioned monocular detector to its multi-modal version. We name the designed monocular and multi-modal detectors as UniMODE and MM-UniMODE, respectively.
  arXiv  Detail & Related papers  (2024-02-28T18:59:31Z)
• Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning [93.71280187657831]
  Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. We propose IA-BEV, which integrates image-plane instance awareness into the depth estimation process within a BEV-based detector.
  arXiv  Detail & Related papers  (2023-12-13T09:24:42Z)
• BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection [47.7933708173225]
  Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. This paper introduces a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks.
  arXiv  Detail & Related papers  (2023-12-04T07:35:02Z)
• OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection [29.530177591608297]
  Multi-view 3D object detection is becoming popular in autonomous driving due to its high effectiveness and low cost. Most of the current state-of-the-art detectors follow the query-based bird's-eye-view (BEV) paradigm. We propose an Object-Centric query-BEV detector OCBEV, which can carve the temporal and spatial cues of moving targets more effectively.
  arXiv  Detail & Related papers  (2023-06-02T17:59:48Z)
• BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy [58.92659367605442]
  We present BEV-IO, a new 3D detection paradigm to enhance BEV representation with instance occupancy information. We show that BEV-IO can outperform state-of-the-art methods while only adding a negligible increase in parameters and computational overhead.
  arXiv  Detail & Related papers  (2023-05-26T11:16:12Z)
• LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation [38.38852904444365]
  This paper proposes a novel scene representation that encodes both the semantics and geometry of the 3D environment in 2D. Our simple yet effective design can be easily integrated into most state-of-the-art 3D object detectors.
  arXiv  Detail & Related papers  (2023-04-04T04:05:56Z)
• OA-BEV: Bringing Object Awareness to Bird's-Eye-View Representation for Multi-Camera 3D Object Detection [78.38062015443195]
  OA-BEV is a network that can be plugged into the BEV-based 3D object detection framework. Our method achieves consistent improvements over the BEV-based baselines in terms of both average precision and nuScenes detection score.
  arXiv  Detail & Related papers  (2023-01-13T06:02:31Z)
• Rethinking Dimensionality Reduction in Grid-based 3D Object Detection [24.249147412551768]
  We propose a novel point cloud detection network based on a Multi-level feature dimensionality reduction strategy, called MDRNet. In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation. Experiments on nuScenes show that the proposed method outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-09-20T04:51:54Z)
• BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View [117.44028458220427]
  On-board 3D object detection in autonomous vehicles often relies on geometry information captured by LiDAR devices. We present a fully end-to-end 3D object detection framework that can infer oriented 3D boxes solely from BEV images.
  arXiv  Detail & Related papers  (2020-03-09T15:08:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.