# Fine-scale Surface Normal Estimation using a Single NIR Image

arXiv: https://arxiv.org/abs/1603.07475 · HTML: https://mlsanity.com/paper/1603.07475/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2016.

## Built on by (most cited first, 2 of 2)

- [Monocular Normal Estimation via Shading Sequence Estimation](https://mlsanity.com/paper/2602.09929/) (2026)
- [Ambient-robust Inverse Rendering using Active RGB-NIR Imaging](https://mlsanity.com/paper/2605.30250/) (2026)

## Abstract (arXiv)

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.