Designing Deep Networks for Surface Normal Estimation

11/18/2014
by   Xiaolong Wang, et al.
0

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture we should use? We propose to build upon the decades of hard work in 3D scene understanding, to design new CNN architecture for the task of surface normal estimation. We show by incorporating several constraints (man-made, manhattan world) and meaningful intermediate representations (room layout, edge labels) in the architecture leads to state of the art performance on surface normal estimation. We also show that our network is quite robust and show state of the art results on other datasets as well without any fine-tuning.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 7

page 8

research
12/27/2018

Surface Networks via General Covers

Developing deep learning techniques for geometric data is an active and ...
research
11/18/2014

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

In this paper we address three different computer vision tasks using a s...
research
03/24/2016

Fine-scale Surface Normal Estimation using a Single NIR Image

We present surface normal estimation using a single near infrared (NIR) ...
research
07/03/2016

A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method

The task of estimating the spatial layout of cluttered indoor scenes fro...
research
07/17/2020

Surface Normal Estimation of Tilted Images via Spatial Rectifier

In this paper, we present a spatial rectifier to estimate surface normal...
research
01/22/2020

AutoFCL: Automatically Tuning Fully Connected Layers for Transfer Learning

Deep Convolutional Neural Networks (CNN) have evolved as popular machine...
research
03/15/2018

LEGO: Learning Edge with Geometry all at Once by Watching Videos

Learning to estimate 3D geometry in a single image by watching unlabeled...

Please sign up or login with your details

Forgot password? Click here to reset