PS-GS: Gaussian Splatting for Multi-View Photometric Stereo
By: Yixiao Chen , Bin Liang , Hanzhi Guo and more
Potential Business Impact:
Makes 3D models from pictures, better than before.
Integrating inverse rendering with multi-view photometric stereo (MVPS) yields more accurate 3D reconstructions than the inverse rendering approaches that rely on fixed environment illumination. However, efficient inverse rendering with MVPS remains challenging. To fill this gap, we introduce the Gaussian Splatting for Multi-view Photometric Stereo (PS-GS), which efficiently and jointly estimates the geometry, materials, and lighting of the object that is illuminated by diverse directional lights (multi-light). Our method first reconstructs a standard 2D Gaussian splatting model as the initial geometry. Based on the initialization model, it then proceeds with the deferred inverse rendering by the full rendering equation containing a lighting-computing multi-layer perceptron. During the whole optimization, we regularize the rendered normal maps by the uncalibrated photometric stereo estimated normals. We also propose the 2D Gaussian ray-tracing for single directional light to refine the incident lighting. The regularizations and the use of multi-view and multi-light images mitigate the ill-posed problem of inverse rendering. After optimization, the reconstructed object can be used for novel-view synthesis, relighting, and material and shape editing. Experiments on both synthetic and real datasets demonstrate that our method outperforms prior works in terms of reconstruction accuracy and computational efficiency.
Similar Papers
Multiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fields
CV and Pattern Recognition
Makes 3D pictures look more real and smooth.
Unposed 3DGS Reconstruction with Probabilistic Procrustes Mapping
CV and Pattern Recognition
Creates detailed 3D worlds from many photos.
3D Gaussian Inverse Rendering with Approximated Global Illumination
Graphics
Makes 3D scenes look real with changing light.