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)
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt età la di↵usion(More)
We explore architectures for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation. Convolutional predictors, such as the fully-convolutional network (FCN), have achieved remarkable success by exploiting the spatial redundancy of neighboring pixels through(More)
Truly understanding a scene involves reasoning not just about what is visible but also about what is not visible. Consider for example the images in Figure 1. After we recognize an object as a chair, we have a pretty good sense of how far it extends in depth and what it might look like from another viewpoint. One way of achieving this kind of understanding(More)
  • Bryan T Russell, Bryan Russell, Brian Leiter, Paul Katsafanas, Daniel Wegner, Benjamin Libet +4 others
  • 2015
Brian Leiter is one of the few Nietzsche interpreters who argue that Nietzsche rejects all forms of free will. Leiter argues that Nietzsche is an incompatibilist and rejects libertarian free will. He further argues that since Nietzsche is an epiphenomenalist about conscious willing, his philosophy of action cannot support any conception of free will. Leiter(More)
We are interested in learning how to exploit continuity, motion and context to account for stable, recov-erable, spatiotemporal phenomena embedded in video. While most humans can make sense of still images, for the most part, we need continuity and motion to make sense of the world around us. Humans are also aided by strong priors that allow us to make(More)
  • 1