What Is Around The Camera?
This work addresses the challenge of scene understanding for computer vision applications, representing an incremental advance in leveraging object reflections for environment prediction.
The paper tackles the problem of estimating the surrounding environment from a single image by analyzing reflections on foreground objects, proposing a learning-based method that jointly models environment and material statistics, achieving improved performance when objects are made of multiple materials.
How much does a single image reveal about the environment it was taken in? In this paper, we investigate how much of that information can be retrieved from a foreground object, combined with the background (i.e. the visible part of the environment). Assuming it is not perfectly diffuse, the foreground object acts as a complexly shaped and far-from-perfect mirror. An additional challenge is that its appearance confounds the light coming from the environment with the unknown materials it is made of. We propose a learning-based approach to predict the environment from multiple reflectance maps that are computed from approximate surface normals. The proposed method allows us to jointly model the statistics of environments and material properties. We train our system from synthesized training data, but demonstrate its applicability to real-world data. Interestingly, our analysis shows that the information obtained from objects made out of multiple materials often is complementary and leads to better performance.