pith. sign in

arxiv: 1908.09492 · v1 · pith:DEQLVIXKnew · submitted 2019-08-26 · 💻 cs.CV

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

Benjin Zhu , Zhengkai Jiang , Xiangxin Zhou , Zeming Li , Gang Yu This is my paper
classification 💻 cs.CV
keywords detectionclass-balancedautonomousbalancedchallengedrivingobjectperformance
0
0 comments X
read the original abstract

This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categories withsimilar shapes. Based on the Challenge results, our methodoutperforms the PointPillars [14] baseline by a large mar-gin across all metrics, achieving state-of-the-art detection performance on the nuScenes dataset. Code will be released at CBGS.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. nuScenes: A multimodal dataset for autonomous driving

    cs.LG 2019-03 accept novelty 8.0

    nuScenes provides the first public autonomous-driving dataset that includes synchronized 360-degree data from cameras, radars, and lidar together with 3D bounding-box annotations across 1000 scenes.

  2. GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception

    cs.CV 2026-07 unverdicted novelty 7.0

    GaussianFusion presents a 3D Gaussian-based framework that unifies multi-modal features in continuous space for 3D object detection and semantic occupancy, reporting gains over BEVFusion and GaussFormer on nuScenes.

  3. ATLAS: A Large-Scale Evaluation Benchmark for Adversarial LiDAR Perception

    cs.CV 2026-06 unverdicted novelty 7.0

    ATLAS is the first large-scale benchmark for black-box adversarial attacks on LiDAR perception, revealing that stronger clean-data models are more vulnerable to point injection due to object database sampling augmentations.

  4. SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Cameras

    cs.CV 2026-05 unverdicted novelty 6.0

    SimPB++ unifies multi-view 2D perspective and 3D BEV object detection in one model via an interactive hybrid decoder, reporting state-of-the-art results on nuScenes and long-range detection up to 150 m on Argoverse2.

  5. CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras

    cs.CV 2026-04 unverdicted novelty 6.0

    CAM3DNet outperforms prior camera-based 3D detectors on nuScenes, Waymo and Argoverse by using three new modules to better mine multi-scale spatiotemporal features from 2D queries and pyramid maps.

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

    cs.CV 2025-05 unverdicted novelty 6.0

    RQR3D reparametrizes oriented bounding box regression in BEV 3D detection as regressing a horizontal box plus corner offsets and achieves SOTA camera-radar performance on nuScenes with 67.5 NDS and 59.7 mAP.

  7. BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

    cs.CV 2021-12 conditional novelty 6.0

    BEVDet achieves 39.3% mAP and 47.2% NDS on nuScenes val set with a fast BEV-based multi-camera 3D detector that outperforms FCOS3D while using far less compute in its tiny variant.

  8. Camera and LiDAR BEV Fusion for Cooperative 3D Object Detection on TUMTraf V2X

    cs.CV 2026-06 unverdicted novelty 5.0

    A roadside-camera plus infrastructure-vehicle LiDAR fusion model reaches 0.85 mAP on TUMTraf V2X but 44 of 50 test frames overlap with the released train and validation splits.

  9. Can BEV Perception Gracefully Degrade under Sensor Failures?

    cs.CV 2026-05 unverdicted novelty 5.0

    Grace-BEV enables graceful degradation in BEV perception under sensor failures by using a TrustGate Router for modality trustworthiness and FailSafe Fusion Block for dynamic integration, with modality dropout training...

  10. SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection

    cs.CV 2026-04 unverdicted novelty 5.0

    SemLT3D introduces semantic-guided expert distillation with a language MoE module and CLIP projection to enrich features for long-tailed classes in camera-only 3D detection.

  11. Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation

    cs.CV 2026-04 unverdicted novelty 5.0

    CTAB exchanges features between detection and segmentation via multi-scale deformable attention in BEV space, yielding segmentation gains on 7 nuScenes classes at neutral detection cost.

  12. Class-Adaptive Cooperative Perception for Multi-Class LiDAR-based 3D Object Detection in V2X Systems

    cs.CV 2026-04 unverdicted novelty 5.0

    A new class-adaptive fusion architecture improves multi-class LiDAR 3D object detection in V2X cooperative perception by routing small and large objects through attentive pathways and balancing training objectives.

  13. All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles

    cs.CV 2025-10 unverdicted novelty 4.0

    A survey synthesizing sensor fusion strategies, AV datasets, and emerging LLM/VLM-powered object detection pipelines for autonomous vehicles.