dinov3_ros
ROS 2 integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.
- 109
- Python
- Apache-2.0
- 13 mo ago
Raessan
Built from Raessan's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
ROS 2 integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.
DeepStream integration of Meta’s DINOv3 backbone with lightweight heads for vision tasks.
Real-time monocular depth estimation with Depth Anything V3 and NVIDIA DeepStream 8.0.
Lightweight head for depth estimation using DINOv3 as backbone
Lightweight head for object detection using DINOv3 as backbone
Lightweight head for semantic segmentation using DINOv3 as backbone
Lightweight head for optical flow using DINOv3 as backbone
Code to perform radar and camera fusion with a NN and the NuScenes dataset. Lidar is used for supervision
Code designed during my PhD involving a rehabilitation robot with model-based and learning controllers
Using computer vision to read characters in a videogame and translate. A good way to learn a language!