[paper] 00040-Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale

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

Paper:

Author:

David Eigen: Dept. of Computer Science, Courant Institute, New York University

Rob Fergus: FaceBook AI Research

Abstract:

1. multiscal conv : depth prediction, surface normal estimation, and semantic labeling.

2. refines predictions using a sequence of scales, and captures many image details without and superpixels or low-level segmentation.

1. Introduction

In this paper, we address three of these tasks, depth prediction,surface normal estimation and semantic segmentation— all using a single common architecture.

Several advantages:

First, appropriate training set and loss function.

Second, simplify the implementation of systems that require multiple modalities.

Third, much of the computation can be shared between modalities , making the system more efficient.

2. Related Work

Most of these systems use ConvNets to find only local features, or generate descriptors of discrete proposal regions; by contrast, our network uses both local and global views to predict a variety of output types.

3. Model Architecture