no code implementations • 18 Apr 2024 • Julian Ost, Tanushree Banerjee, Mario Bijelic, Felix Heide
We propose to recast 3D multi-object tracking from RGB cameras as an \emph{Inverse Rendering (IR)} problem, by optimizing via a differentiable rendering pipeline over the latent space of pre-trained 3D object representations and retrieve the latents that best represent object instances in a given input image.