Fine-scale Surface Normal Estimation using a Single NIR Image
arXiv:1603.07475
Abstract
We present surface normal estimation using a single near infrared (NIR) image. We are focusing on fine-scale surface geometry captured with an uncalibrated light source. To tackle this ill-posed problem, we adopt a generative adversarial network which is effective in recovering a sharp output, which is also essential for fine-scale surface normal estimation. We incorporate angular error and integrability constraint into the objective function of the network to make estimated normals physically meaningful. We train and validate our network on a recent NIR dataset, and also evaluate the generality of our trained model by using new external datasets which are captured with a different camera under different environment.
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Deep multi-scale video prediction beyond mean square error
- Image Super-Resolution Using Deep Convolutional Networks
- DeepStereo: Learning to Predict New Views from the World's Imagery
- Accurate Image Super-Resolution Using Very Deep Convolutional Networks
- AttentionNet: Aggregating Weak Directions for Accurate Object Detection
- Deep Reflectance Maps