RotatedMVPS: Multi-view Photometric Stereo with Rotated Natural Light
By: Songyun Yang , Yufei Han , Jilong Zhang and more
Potential Business Impact:
Makes 3D shapes from pictures in any light.
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.
Similar Papers
Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cues
CV and Pattern Recognition
Makes 3D cameras see shapes better in any light.
PS-GS: Gaussian Splatting for Multi-View Photometric Stereo
Graphics
Makes 3D models from pictures, better than before.
MVTOP: Multi-View Transformer-based Object Pose-Estimation
CV and Pattern Recognition
Helps robots see objects from many angles.