Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
arXiv:1803.06641
Abstract
Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities for stereo pairs in the target domain. In this work, we propose a self-adaptation approach for CNN training, utilizing both synthetic training data (with ground-truth disparities) and stereo pairs in the new domain (without ground-truths). Our method is driven by two empirical observations. By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details. To avoid i) while exploiting ii), we formulate an iterative optimization problem with graph Laplacian regularization. At each iteration, the CNN adapts itself better to the new domain: we let the CNN learn its own higher-resolution output; at the meanwhile, a graph Laplacian regularization is imposed to discriminatively keep the desired edges while smoothing out the artifacts. We demonstrate the effectiveness of our method in two domains: daily scenes collected by smartphone cameras, and street views captured in a driving car.
arXiv commentAccepted at CVPR 2018
References in corpus (10)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Fully Convolutional Networks for Semantic Segmentation
- DeMoN: Depth and Motion Network for Learning Monocular Stereo
- Virtual Worlds as Proxy for Multi-Object Tracking Analysis
- End-to-End Learning of Geometry and Context for Deep Stereo Regression
- Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain
- Self-Supervised Learning for Stereo Matching with Self-Improving Ability
- Semi-Supervised Deep Learning for Monocular Depth Map Prediction
- Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching