Awesome-BEV-Perception

Papers related to BEV perception

Preliminaries

• DETR
• Deformable DETR

3D detection

• DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries [paper] [Github]
• PETR: Position Embedding Transformation for Multi-View 3D Object Detection [paper][Github]
• Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection [paper]
• BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View [paper] [Github]
• Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D [paper] [Github]

3D semantic seg

• BEVSegFormer: Bird’s Eye View Semantic Segmentation From Arbitrary Camera Rigs [paper]
• CVT: Cross-view Transformers for real-time Map-view Semantic Segmentation [paper] [Github]

3D detection + semantic seg

• BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving [paper] [Github]
• PolarDETR: Polar Parametrization for Vision-based Surround-View 3D Detection[paper] [Github]
• PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images [paper][Github]
• FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras [paper] [Github]

Spatio + temporal BEV

• BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers [paper] [Github]
• BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection [paper]