Learning Object Manipulation Skills from Video via Approximate Differentiable Physics
Vladimír Petrík,Mohammad Nomaan Qureshi,Josef Sivic,Makar Tapaswi,Vladimír Petrík,Mohammad Nomaan Qureshi,Josef Sivic,Makar Tapaswi
We aim to teach robots to perform simple object manipulation tasks by watching a single video demonstration. Towards this goal, we propose an optimization approach that outputs a coarse and temporally evolving 3D scene to mimic the action demonstrated in the input video. Similar to previous work, a differentiable renderer ensures perceptual fidelity between the 3D scene and the 2D video. Our key n...
