Active stereo cameras that recover depth from structured light captures have become a cornerstone sensor modality for 3D scene reconstruction and understanding tasks across application domains. Existing active stereo cameras project a pseudo-random dot pattern on object surfaces to extract disparity independently of object texture. Such hand-crafted patterns are designed in isolation from the scene statistics, ambient illumination conditions, and the reconstruction method. In this work, we propose the first method to jointly learn structured illumination and reconstruction, parameterized by a diffractive optical element and a neural network, in an end-to-end fashion. To this end, we introduce a novel differentiable image formation model for active stereo, relying on both wave and geometric optics, and a novel trinocular reconstruction network. The jointly optimized pattern, which we dub Polka Lines, together with the reconstruction network, achieve state-of-the-art active-stereo depth estimates across imaging conditions. We validate the proposed method in simulation and on a hardware prototype, and show that our method outperforms existing active stereo systems.
تحميل البحث