Experimenting with YOLOv11: 2D/3D Detection, Tracking, and Depth in Under Two Days

I've been experimenting with YOLOv11 recently, and I was genuinely surprised by how easy it is to use — it delivers accurate results with minimal effort.

In less than two days, I was able to get all of the following working:

• 2D bounding boxes — standard object detection
• 3D bounding boxes — spatial localization of objects in 3D
• Object tracking — multi-object tracking across frames
• Depth estimation — per-object depth from a monocular camera

Achieving all of this within just a few days would have been nearly impossible with earlier YOLO versions. It's a testament to how much the ecosystem has matured — the API is clean, the pre-trained models are strong out of the box, and the documentation has caught up with the capabilities.

Having previously spent considerable time with YOLOv5 and YOLOv8, the jump to v11 feels significant. What once required careful pipeline engineering around separate tools now comes bundled and works cohesively. The progress is real, and I'm genuinely enjoying seeing how far YOLO has come.