Skip to yearly menu bar Skip to main content


Poster

SAOR: Single-View Articulated Object Reconstruction

Mehmet Aygun · Oisin Mac Aodha

Arch 4A-E Poster #68
[ ] [ Paper PDF ]
[ Poster
Thu 20 Jun 10:30 a.m. PDT — noon PDT

Abstract:

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.

Chat is not available.