IEEE Trans Vis Comput Graph. 2017 Nov;23(11):2485-2493. doi: 10.1109/TVCG.2017.2734538. Epub 2017 Aug 10.
Predicting specularities in images, given the camera pose and scene geometry from SLAM, forms a challenging and open problem. It is nonetheless essential in several applications such as retexturing. A recent geometric model called JOLIMAS partially answers this problem, under the assumptions that the specularities are elliptical and the scene is planar. JOLIMAS models a moving specularity as the image of a fixed 3D quadric. We propose dual JOLIMAS, a new model which raises the planarity assumption. It uses the fact that specularities remain elliptical on convex surfaces and that every surface can be divided in convex parts. The geometry of dual JOLIMAS then uses a 3D quadric per convex surface part and light source, and predicts the specularities by a means of virtual cameras, allowing it to cope with surface's unflatness. We assessed the efficiency and precision of dual JOLIMAS on multiple synthetic and real videos with various objects and lighting conditions. We give results of a retexturing application. Further results are presented as supplementary video material.
给定 SLAM 中的相机姿态和场景几何形状来预测图像中的镜面反射，这是一个具有挑战性和开放性的问题。然而，在一些应用中，如重新纹理化，它是必不可少的。最近的一个名为 JOLIMAS 的几何模型在镜面反射是椭圆形且场景是平面的假设下部分解决了这个问题。JOLIMAS 将移动镜面反射建模为固定 3D 二次曲面的图像。我们提出了对偶 JOLIMAS，这是一个新的模型，它提高了平面性假设。它利用了这样一个事实，即在凸表面上镜面反射仍然是椭圆形的，并且每个表面都可以分为凸部分。然后，对偶 JOLIMAS 的几何形状使用每个凸表面部分和光源的 3D 二次曲面，并通过虚拟相机来预测镜面反射，从而能够处理表面的不平整度。我们在具有各种物体和光照条件的多个合成和真实视频上评估了对偶 JOLIMAS 的效率和精度。我们给出了重新纹理化应用的结果。更多结果作为补充视频材料呈现。
