Bryan Russell

Learn More
Figure 1. Given a single 2D image, we predict surface normals that capture detailed object surfaces. We use the image and predicted surface normals to retrieve a 3D model from a large library of object CAD models. Abstract We introduce an approach that leverages surface normal predictions, along with appearance cues, to retrieve 3D models for objects(More)
(b)$Edge$Detec)on$ Our&Approach& Ground&Truth& Input&Image& Figure 1. Our framework used for two different pixel prediction problems with minor modification of the architecture (last layer) and training process (epochs). Note how our approach recovers the fine details missing in the ground truth segmentation (left), and achieves state-of-the-art on edge(More)
This paper introduces an approach to regularize 2.5D surface normal and depth predictions at each pixel given a single input image. The approach infers and reasons about the underlying 3D planar surfaces depicted in the image to snap predicted normals and depths to inferred planar surfaces, all while maintaining fine detail within objects. Our approach(More)
  • 1