TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Multi-View 3D Object Detection Network for Autonomous Driv...

Multi-View 3D Object Detection Network for Autonomous Driving

Xiaozhi Chen, Huimin Ma, Ji Wan, Bo Li, Tian Xia

2016-11-23CVPR 2017 7Autonomous Drivingobject-detectionObject Proposal Generation3D Object DetectionObject Detection
PaperPDFCodeCodeCode

Abstract

This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the bird's eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 10.3% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.

Results

TaskDatasetMetricValueModel
Object DetectionKITTI Cars Hard valAP56.56MV3D
Object DetectionKITTI Cars Moderate valAP62.68MV3D
Object DetectionKITTI Cars Easy valAP71.29MV3D
Object DetectionKITTI Cars Easy valAP71.19MV3D (LiDAR)
3DKITTI Cars Hard valAP56.56MV3D
3DKITTI Cars Moderate valAP62.68MV3D
3DKITTI Cars Easy valAP71.29MV3D
3DKITTI Cars Easy valAP71.19MV3D (LiDAR)
Birds Eye View Object DetectionKITTI Cars Hard valAP76.33MV (BV+FV)
Birds Eye View Object DetectionKITTI Cars Moderate valAP77.32MV (BV+FV)
Birds Eye View Object DetectionKITTI Cars Easy valAP86.18MV (BV+FV)
3D Object DetectionKITTI Cars Hard valAP56.56MV3D
3D Object DetectionKITTI Cars Moderate valAP62.68MV3D
3D Object DetectionKITTI Cars Easy valAP71.29MV3D
3D Object DetectionKITTI Cars Easy valAP71.19MV3D (LiDAR)
2D ClassificationKITTI Cars Hard valAP56.56MV3D
2D ClassificationKITTI Cars Moderate valAP62.68MV3D
2D ClassificationKITTI Cars Easy valAP71.29MV3D
2D ClassificationKITTI Cars Easy valAP71.19MV3D (LiDAR)
2D Object DetectionKITTI Cars Hard valAP56.56MV3D
2D Object DetectionKITTI Cars Moderate valAP62.68MV3D
2D Object DetectionKITTI Cars Easy valAP71.29MV3D
2D Object DetectionKITTI Cars Easy valAP71.19MV3D (LiDAR)
16kKITTI Cars Hard valAP56.56MV3D
16kKITTI Cars Moderate valAP62.68MV3D
16kKITTI Cars Easy valAP71.29MV3D
16kKITTI Cars Easy valAP71.19MV3D (LiDAR)

Related Papers

GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous Driving2025-07-19AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework2025-07-18World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving2025-07-17Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models2025-07-17Channel-wise Motion Features for Efficient Motion Segmentation2025-07-17LaViPlan : Language-Guided Visual Path Planning with RLVR2025-07-17A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains2025-07-17RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images2025-07-17