Multi-View Azimuth Stereo via Tangent Space Consistency
This addresses a problem in computer vision for applications like robotics or inspection, offering a novel approach but with incremental improvements over existing photometric stereo methods.
The paper tackles 3D reconstruction from multi-view azimuth maps, achieving accurate shape recovery for textureless or specular surfaces without needing zenith angles.
We present a method for 3D reconstruction only using calibrated multi-view surface azimuth maps. Our method, multi-view azimuth stereo, is effective for textureless or specular surfaces, which are difficult for conventional multi-view stereo methods. We introduce the concept of tangent space consistency: Multi-view azimuth observations of a surface point should be lifted to the same tangent space. Leveraging this consistency, we recover the shape by optimizing a neural implicit surface representation. Our method harnesses the robust azimuth estimation capabilities of photometric stereo methods or polarization imaging while bypassing potentially complex zenith angle estimation. Experiments using azimuth maps from various sources validate the accurate shape recovery with our method, even without zenith angles.