Appearance and Shape from Water Reflection
This work introduces a novel self-calibrating method for 3D reconstruction from water reflections, potentially benefiting fields like computer vision and photography by enabling new applications from accidental catadioptric setups.
The paper tackles the problem of reconstructing 3D geometry and high-dynamic range appearance from a single image that includes water reflections, by treating the reflection as an additional viewpoint in a stereo pair and disentangling scene radiometry and geometry through an iterative method, demonstrating results on real-world images.
This paper introduces single-image geometric and appearance reconstruction from water reflection photography, i.e., images capturing direct and water-reflected real-world scenes. Water reflection offers an additional viewpoint to the direct sight, collectively forming a stereo pair. The water-reflected scene, however, includes internally scattered and reflected environmental illumination in addition to the scene radiance, which precludes direct stereo matching. We derive a principled iterative method that disentangles this scene radiometry and geometry for reconstructing 3D scene structure as well as its high-dynamic range appearance. In the presence of waves, we simultaneously recover the wave geometry as surface normal perturbations of the water surface. Most important, we show that the water reflection enables calibration of the camera. In other words, for the first time, we show that capturing a direct and water-reflected scene in a single exposure forms a self-calibrating HDR catadioptric stereo camera. We demonstrate our method on a number of images taken in the wild. The results demonstrate a new means for leveraging this accidental catadioptric camera.