데이터셋
- Openlane
- ApolloSim
- Once 등
3d lane detection 구조 논문
- 3D-LaneNet: End-to-End 3D Multiple Lane Detection
- Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection
- PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
- Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraint (CLGO)
- Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection
- LATR: 3DLaneDetection from Monocular Images with Transformer
- LaneCPP: Continuous 3D Lane Detection using Physical Priors
EigenLane
- Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes [CVPR 2022]
기타 알아야할 것
- DETR End-to-End Object Detection with Transformers
- Deformable convolution / transformer
- World(Ground) coordinate, Camera coordinate
- Coordinate transform matrix
- Camera parameter (intrinsic, extrinsic)
