A battery-powered Raspberry Pi 5 perception system that captures monocular images, estimates camera motion, reconstructs sparse and dense 3D structure, and reports quantitative reconstruction quality.
Official PyTorch implementation of Geometry-grounded Point Transformer (GGPT) (CVPR 2026). GGPT is a method for high-quality 3D reconstruction from multiview images ...
It reminded me of a project I built during my university days in 2023, a real-time object detection application using Python and YOLOv5 that could identify and track objects through a live camera feed ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results