DRACO: Weakly Supervised Dense Reconstruction And Canonicalization of Objects

Rahul Sajnani1    AadilMehdi Sanchawala1    Krishna Murthy Jatavallabhula2    Srinath Sridhar3    K. Madhava Krishna1   

1 International Institute of Information Technology, Hyderabad    2 Mila, Universite de Montreal, Canada    3 Brown University, RI   

We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images. Canonical shape reconstruction— estimating 3D object shape in a coordinate space canonicalized for scale, rotation, and translation parameters—is an emerging paradigm that holds promise for a multitude of robotic applications. Prior approaches either rely on painstakingly gathered dense 3D supervision, or produce only sparse canonical representations, limiting real-world applicability. DRACO performs dense canonicalization using only weak supervision in the form of camera poses and semantic keypoints at train time. During inference, DRACO predicts dense object-centric depth maps in a canonical coordinate-space, solely using one or more RGB images of an object. Extensive experiments on canonical shape reconstruction and pose estimation show that DRACO is competitive or superior to fully-supervised methods.