https://github.com/ZRandomize/MatrixVT
공식 코드MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
Papers with Code 아카이브
Bird's-Eye View Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 29
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/bradyz/cross_view_transformers
공식 코드Cross-view Transformers for real-time Map-view Semantic Segmentation
https://github.com/d1024choi/progressivequeryrefinenet
공식 코드https://github.com/derrickxunu/cobevt
공식 코드CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
https://github.com/goodarzmehr/simbev
공식 코드SimBEV: A Synthetic Multi-Task Multi-Sensor Driving Data Generation Tool and Dataset
https://github.com/happytianhao/tade
공식 코드Improving Bird's Eye View Semantic Segmentation by Task Decomposition
https://github.com/junyu-z/semi-bevseg
공식 코드Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentation
https://github.com/megvii-research/petr
공식 코드PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
https://github.com/nv-tlabs/lift-splat-shoot
공식 코드Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D
https://github.com/valeoai/LaRa
공식 코드LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation
https://github.com/valeoai/pointbev
공식 코드https://github.com/wayveai/fiery
공식 코드FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
https://github.com/wayveai/mile
공식 코드https://github.com/zhiqi-li/BEVFormer
공식 코드https://github.com/MortenTabaka/Semantic-segmentation-of-LandCover.ai-dataset
https://github.com/fundamentalvision/BEVFormer
https://github.com/megvii-basedetection/bevdepth
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
https://github.com/opendrivelab/st-p3
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
https://github.com/refkxh/DUSA
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.