3D Object Tracking without Training Data? In our @Nature Machine Intelligence paper (https://www.nature.com/articles/s42256-025-01083-x?error=cookies_not_supported&code=8393fd2c-9a65-4f03-a43e-ea2a761a4927), we recast 3D tracking as an inverse neural rendering task where we fit a scene graph to an image that best explains this image. The method generalizes to completely unseen datasets and is explainable.
Project and Code: https://light.princeton.edu/publication/inverse-rendering-tracking/
Fun collaboration between @PrincetonCS and Torc Robotics, with Julian Ost and Tanushree Banerjee leading this project.