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

ICCV 2015  ·  David Eigen, Rob Fergus ·

In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily 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 segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.

PDF Abstract ICCV 2015 PDF ICCV 2015 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Monocular Depth Estimation NYU-Depth V2 Eigen et al. RMSE 0.641 # 72


No methods listed for this paper. Add relevant methods here