SAOR: Single-View Articulated Object Reconstruction
This addresses the challenge of 3D reconstruction for articulated objects in uncontrolled settings, offering a more flexible approach than category-specific methods, though it is incremental in its domain.
The paper tackles the problem of reconstructing 3D articulated objects from single images without relying on pre-defined templates or skeletons, achieving improved results on quadruped animals compared to prior methods.
We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild. Unlike prior approaches that rely on pre-defined category-specific 3D templates or tailored 3D skeletons, SAOR learns to articulate shapes from single-view image collections with a skeleton-free part-based model without requiring any 3D object shape priors. To prevent ill-posed solutions, we propose a cross-instance consistency loss that exploits disentangled object shape deformation and articulation. This is helped by a new silhouette-based sampling mechanism to enhance viewpoint diversity during training. Our method only requires estimated object silhouettes and relative depth maps from off-the-shelf pre-trained networks during training. At inference time, given a single-view image, it efficiently outputs an explicit mesh representation. We obtain improved qualitative and quantitative results on challenging quadruped animals compared to relevant existing work.