A Chinese lab taught a vision model to stop getting lost in 3D, and it beat general AI on robot tracking
Picture a robot watering flowers in order, holding the spout a few centimetres above each bloom. Getting that right is easy for people and hard for general AI, and a Chinese team behind RoboTracer argues the problem is how vision models represent space. Why general models get lost in 3D RoboTracer drops XYZ coordinates in … Read more