SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
arXiv:2006.04026
Abstract
We propose a novel method for combining synthetic and real images when training networks to determine geometric information from a single image. We suggest a method for mapping both image types into a single, shared domain. This is connected to a primary network for end-to-end training. Ideally, this results in images from two domains that present shared information to the primary network. Our experiments demonstrate significant improvements over the state-of-the-art in two important domains, surface normal estimation of human faces and monocular depth estimation for outdoor scenes, both in an unsupervised setting.
Accepted to CVPR 2020. Supplementary material added towards the end instead of a separate file. A Github link to the code is also provided in this submission
References in corpus (11)
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
- Unsupervised Cross-Domain Image Generation
- Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
- Virtual Worlds as Proxy for Multi-Object Tracking Analysis
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- Unsupervised Learning of Depth and Ego-Motion from Video
- Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
- Neural Face Editing with Intrinsic Image Disentangling