Aperture Supervision for Monocular Depth Estimation
Authors:
Preprint
Abstract
We present a novel method to train machine learning algorithms to estimate scene depths from a single image, by using the information provided by a camera's aperture as supervision. Prior works use a depth sensor's outputs or images of the same scene from alternate viewpoints as supervision, while our method instead uses images from the same viewpoint taken with a varying camera aperture. To enable learning algorithms to use aperture effects as supervision, we introduce two differentiable aperture rendering functions that use the input image and predicted depths to simulate the depth-of-field effects caused by real camera apertures. We train a monocular depth estimation network end-to-end to predict the scene depths that best explain these finite aperture images as defocus-blurred renderings of the input all-in-focus image.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- Deeper Depth Prediction with Fully Convolutional Residual Networks2016
- The Fast Bilateral Solver2016
- Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks2016
- 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction2016
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue2016
- Fast bilateral-space stereo for synthetic defocus2015
- Shape-from-shading: a surveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- Computing Local Surface Orientation and Shape from Texture for Curved SurfacesInternational Journal of Computer Vision, 1997
- Recovering surface shape and orientation from textureArtificial Intelligence, 1981