Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

David Eigen, Rob Fergus
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
In this paper we address three different computer vision tasks using a single multiscale convolutional network architecture: depth prediction, surface normal estimation, and semantic labeling. The network that we develop is able to adapt naturally to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level
more » ... s or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.
doi:10.1109/iccv.2015.304 dblp:conf/iccv/EigenF15 fatcat:asamviz5ezg3fnv2ywbdxhh3bm