RotatedMVPS: Multi-view Photometric Stereo with Rotated Natural Light
This addresses the limitation of MVPS methods for natural illumination scenarios and downstream inverse rendering tasks, representing an incremental improvement by integrating existing learning-based priors into a new framework.
The paper tackled the problem of recovering high-fidelity surface shapes and reflectances in multiview photometric stereo under natural illumination, which existing methods struggle with due to controlled settings or neglect of reflectance recovery. The result was a method that reduces unknowns in complex environment light and integrates data priors, enhancing accuracy as demonstrated on synthetic and real-world datasets.
Multiview photometric stereo (MVPS) seeks to recover high-fidelity surface shapes and reflectances from images captured under varying views and illuminations. However, existing MVPS methods often require controlled darkroom settings for varying illuminations or overlook the recovery of reflectances and illuminations properties, limiting their applicability in natural illumination scenarios and downstream inverse rendering tasks. In this paper, we propose RotatedMVPS to solve shape and reflectance recovery under rotated natural light, achievable with a practical rotation stage. By ensuring light consistency across different camera and object poses, our method reduces the unknowns associated with complex environment light. Furthermore, we integrate data priors from off-the-shelf learning-based single-view photometric stereo methods into our MVPS framework, significantly enhancing the accuracy of shape and reflectance recovery. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of our approach.