Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Hello,
I was thinking of porting the ROS1 package to ROS2 Humble, do you know if such a work has already been done?
As far as I know, the project ros2_torch2trt_examples runs MiDas with ROS2, but it seem to rely on NVDIA GPU and I want to use the package on a Raspberry Pi.
Hello, I was thinking of porting the ROS1 package to ROS2 Humble, do you know if such a work has already been done?
As far as I know, the project ros2_torch2trt_examples runs MiDas with ROS2, but it seem to rely on NVDIA GPU and I want to use the package on a Raspberry Pi.
Another project doing monocular depth is under development here: https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_argus_camera