BePo: Leveraging Birds Eye View and Sparse Points for Efficient and Accurate 3D Occupancy Prediction

• URL: http://arxiv.org/abs/2506.07002v1
• Date: Sun, 08 Jun 2025 05:19:02 GMT
• Title: BePo: Leveraging Birds Eye View and Sparse Points for Efficient and Accurate 3D Occupancy Prediction
• Authors: Yunxiao Shi, Hong Cai, Jisoo Jeong, Yinhao Zhu, Shizhong Han, Amin Ansari, Fatih Porikli,
• Abstract summary: 3D occupancy provides fine-grained 3D geometry and semantics for scene understanding.<n>Bird's Eye View (BEV) or sparse points as scene representation with much reduced cost, but still suffer from their respective shortcomings.<n>We present a novel 3D occupancy prediction approach, BePo, which combines BEV and sparse points based representations.
• Score: 38.9869091446875
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 3D occupancy provides fine-grained 3D geometry and semantics for scene understanding which is critical for autonomous driving. Most existing methods, however, carry high compute costs, requiring dense 3D feature volume and cross-attention to effectively aggregate information. More recent works have adopted Bird's Eye View (BEV) or sparse points as scene representation with much reduced cost, but still suffer from their respective shortcomings. More concretely, BEV struggles with small objects that often experience significant information loss after being projected to the ground plane. On the other hand, points can flexibly model little objects in 3D, but is inefficient at capturing flat surfaces or large objects. To address these challenges, in this paper, we present a novel 3D occupancy prediction approach, BePo, which combines BEV and sparse points based representations. We propose a dual-branch design: a query-based sparse points branch and a BEV branch. The 3D information learned in the sparse points branch is shared with the BEV stream via cross-attention, which enriches the weakened signals of difficult objects on the BEV plane. The outputs of both branches are finally fused to generate predicted 3D occupancy. We conduct extensive experiments on the Occ3D-nuScenes and Occ3D-Waymo benchmarks that demonstrate the superiority of our proposed BePo. Moreover, BePo also delivers competitive inference speed when compared to the latest efficient approaches.

Related papers

• SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection [19.75965521357068]
  We propose a novel approach called SOGDet (Semantic-Occupancy Guided Multi-view 3D Object Detection) to improve the accuracy of 3D object detection. Our results show that SOGDet consistently enhance the performance of three baseline methods in terms of nuScenes Detection Score (NDS) and mean Average Precision (mAP) This indicates that the combination of 3D object detection and 3D semantic occupancy leads to a more comprehensive perception of the 3D environment, thereby aiding build more robust autonomous driving systems.
  arXiv  Detail & Related papers  (2023-08-26T07:38:21Z)
• 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)
• EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection [9.289537252177048]
  We propose a novel Edge-aware Lift-splat-shot (EA-LSS) framework for 3D object detection. Our EA-LSS framework is compatible for any LSS-based 3D object detection models.
  arXiv  Detail & Related papers  (2023-03-31T08:56:29Z)
• 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)
• Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection [35.797350813519756]
  Monocular 3D lane detection is a challenging task due to its lack of depth information. We propose a BEV-free method named Anchor3DLane to predict 3D lanes directly from FV representations.
  arXiv  Detail & Related papers  (2023-01-06T04:35:31Z)
• BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios [51.285561119993105]
  We present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation. We introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder.
  arXiv  Detail & Related papers  (2022-12-12T08:15:03Z)
• BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks [28.024042528077125]
  Bird's-Eye-View (BEV) 3D Object Detection is a crucial multi-view technique for autonomous driving systems. We propose a novel method named BEV Slice Attention Network (BEV-SAN) for exploiting the intrinsic characteristics of different heights.
  arXiv  Detail & Related papers  (2022-12-02T15:14:48Z)
• Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking [9.693724357115762]
  3D single object tracking is a key task in 3D computer vision. The sparsity of point clouds makes it difficult to compute the similarity and locate the object. We propose a sparse-to-dense and transformer-based framework for 3D single object tracking.
  arXiv  Detail & Related papers  (2022-10-02T13:38:30Z)
• Homography Loss for Monocular 3D Object Detection [54.04870007473932]
  A differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information. Our method yields the best performance compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
  arXiv  Detail & Related papers  (2022-04-02T03:48:03Z)
• RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation [11.180128679075716]
  Range-Aware Attention Network (RAANet) is developed for 3D object detection from LiDAR data for autonomous driving. RAANet extracts more powerful BEV features and generates superior 3D object detections. Experiments on nuScenes dataset demonstrate that our proposed approach outperforms the state-of-the-art methods for LiDAR-based 3D object detection.
  arXiv  Detail & Related papers  (2021-11-18T04:20:13Z)
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net [93.51773847125014]
  We propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world.
  arXiv  Detail & Related papers  (2020-12-22T22:43:35Z)

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.