Object Wake-up: 3D Object Reconstruction and Animation from a Single Image

Given a single chair image, could we extract its 3D shape and animate its plausible articulations and motions? This is an interesting new question that may have numerous downstream augmented reality and virtual reality applications. In this paper, we propose an automated approach to tackle the entire process of reconstruct such 3-D generic objects from single images, rigging and animation. Comparing with previous efforts on object manipulation, our work goes beyond 2D manipulation. Moreover, we endow plausible human-like or animal-like deformations to the otherwise rigid-body objects such as chairs; this leads to greater flexibility in terms of feasible object motions. Empirically our approach is demonstrated with satisfactory performance on public datasets as well as our in-house dataset; when compared on the related tasks of 3D reconstruction and skeleton prediction, our results surpass those of the State-of-the-arts by a noticeable margin. Our implementation and dataset are to be made publicly available upon paper acceptance.