K. S. Ernest (iFire) Lee

Convert ONNX to IREE https://github.com/ibaiGorordo/ONNX-SAM2-Segment-Anything See the Google Colab notebook https://colab.research.google.com/drive/1tqdYbjmFq4PK3Di7sLONd0RkKS0hBgId?usp=sharing

Use `SmilingWolf/wd-eva02-large-tagger-v3` to tag the image.

https://github.com/roboflow/rf-detr is currently my most favourable model for this task. rf-detr supports onnx export https://github.com/roboflow/rf-detr?tab=readme-ov-file#onnx-export.

The most valuable problems are Keypoint Detection and Object Detection. I rank keypoint detection above Object Detection. However, using Roboflow to reduce data engineering costs means we must pick their...

In theory, the https://roboflow.com/model/yolo-nas-pose can be used to do keypoint skeleton posing. yolo-nas-pose also has onnx export https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/models_export_pose.md

We can also use the RoboFlow keypoint skeleton annotator to skeleton annotate and train YOLO-nas-pose off the cloud. Let's use the godot engine humanoid skeleton because it locks the bone...

The coco format is described http://cocodataset.org/#format-data for the general COCO format and the keypoint skeleton format. https://cocodataset.org/#panoptic-2020 ~~https://github.com/cvat-ai/cvat is a popular annotation tool.~~ Bad ui. https://github.com/HumanSignal/label-studio

https://store.intelrealsense.com/buy-intel-realsense-lidar-camera-l515.html Is a consumer accessible LIDAR scanner. What data sets would you want and would you recommend patching meshroom to support it? Intel® RealSense™ LiDAR Camera L515 $349.00 USD Edited:...

See https://godotengine.org/article/introducing-the-improved-ufbx-importer-in-godot-4-3/ or https://www.youtube.com/watch?v=TGszmac4Y2k As far as we know there are only improvements.

I want to try getting this merged for Godot Engine Master 4.4. Can we get a rebase on this?