Fine-scale Surface Normal Estimation using a Single NIR Image
This work addresses a domain-specific challenge in computer vision for applications requiring detailed surface geometry from NIR data, but it appears incremental as it builds on existing GAN methods with added constraints.
The paper tackles the problem of estimating fine-scale surface normals from a single near-infrared image with an uncalibrated light source, achieving results by incorporating angular error and integrability constraints into a generative adversarial network, though no concrete numbers are provided in the 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.