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/Disp R-CNN: Stereo 3D Object Detection via Shape Prior Gui...

Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation

Jiaming Sun, Linghao Chen, Yiming Xie, Siyu Zhang, Qinhong Jiang, Xiaowei Zhou, Hujun Bao

2020-04-07CVPR 2020 63D Object Detection From Stereo ImagesVehicle Pose EstimationDisparity Estimationobject-detection3D Object DetectionObject Detection
PaperPDFCode(official)

Abstract

In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a category-specific shape prior for more accurate disparity estimation. To address the challenge from scarcity of disparity annotation in training, we propose to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes our system more widely applicable. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision.

Results

TaskDatasetMetricValueModel
Pose EstimationKITTI Cars HardAverage Orientation Similarity67.16Disp-RCNN (Stereo)
Object DetectionKITTI Cars ModerateAP7545.78Disp R-CNN
Object DetectionKITTI Cyclists ModerateAP5024.4Disp R-CNN
Object DetectionKITTI Pedestrians ModerateAP5025.8Disp R-CNN
3DKITTI Cars ModerateAP7545.78Disp R-CNN
3DKITTI Cyclists ModerateAP5024.4Disp R-CNN
3DKITTI Pedestrians ModerateAP5025.8Disp R-CNN
3DKITTI Cars HardAverage Orientation Similarity67.16Disp-RCNN (Stereo)
3D Object DetectionKITTI Cars ModerateAP7545.78Disp R-CNN
3D Object DetectionKITTI Cyclists ModerateAP5024.4Disp R-CNN
3D Object DetectionKITTI Pedestrians ModerateAP5025.8Disp R-CNN
2D ClassificationKITTI Cars ModerateAP7545.78Disp R-CNN
2D ClassificationKITTI Cyclists ModerateAP5024.4Disp R-CNN
2D ClassificationKITTI Pedestrians ModerateAP5025.8Disp R-CNN
2D Object DetectionKITTI Cars ModerateAP7545.78Disp R-CNN
2D Object DetectionKITTI Cyclists ModerateAP5024.4Disp R-CNN
2D Object DetectionKITTI Pedestrians ModerateAP5025.8Disp R-CNN
1 Image, 2*2 StitchiKITTI Cars HardAverage Orientation Similarity67.16Disp-RCNN (Stereo)
16kKITTI Cars ModerateAP7545.78Disp R-CNN
16kKITTI Cyclists ModerateAP5024.4Disp R-CNN
16kKITTI Pedestrians ModerateAP5025.8Disp R-CNN

Related Papers

A 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 Images2025-07-17Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection2025-07-17Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis2025-07-17Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios2025-07-16Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping2025-07-15ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge2025-07-08Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations2025-07-07