Portal de Periódicos da CAPES

Fine-Scale Surface Normal Estimation Using a Single NIR Image

2016; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-3-319-46487-9_30

1611-3349

Young-Jin Yoon, Gyeongmin Choe, Nam Il Kim, Joon‐Young Lee, In So Kweon,

Computer Graphics and Visualization Techniques

We present surface normal estimation using a single near infrared (NIR) image. We are focusing on reconstructing fine-scale surface geometry using an image captured with an uncalibrated light source. To tackle this ill-posed problem, we adopt a generative adversarial network, which is effective in recovering sharp outputs essential for fine-scale surface normal estimation. We incorporate the angular error and an integrability constraint into the objective function of the network to make the estimated normals incorporate physical characteristics. 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 that are captured with a different camera under different environments.