megvii-research/PETR
Transformer-based 3D object detection and BEV segmentation model that processes multi-camera images using position embedding transformation.
Not currently ranked — collecting fresh signals.
star history
PETR and PETRv2 are deep learning models published at ECCV2022 and ICCV2023 for 3D perception from multi-view camera images. PETR introduces position embedding transformation to encode 3D coordinate information into image features for end-to-end object detection. PETRv2 extends this with temporal modeling to leverage previous frame information and adds a segmentation query set for Bird’s Eye View segmentation tasks.
Frequently asked
- What is megvii-research/PETR?
- Transformer-based 3D object detection and BEV segmentation model that processes multi-camera images using position embedding transformation.
- Is PETR open source?
- Yes — megvii-research/PETR is an open-source project tracked on heatdrop.
- What language is PETR written in?
- megvii-research/PETR is primarily written in Python.
- How popular is PETR?
- megvii-research/PETR has 1.1k stars on GitHub.
- Where can I find PETR?
- megvii-research/PETR is on GitHub at https://github.com/megvii-research/PETR.