Multi-View Mesh Reconstruction With Neural Deferred Shading

Markus Worchel, Rodrigo Diaz, Weiwen Hu, Oliver Schreer, Ingo Feldmann, Peter Eisert; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 6187-6197

We propose an analysis-by-synthesis method for fast multi-view 3D reconstruction of opaque objects with arbitrary materials and illumination. State-of-the-art methods use both neural surface representations and neural rendering. While flexible, neural surface representations are a significant bottleneck in optimization runtime. Instead, we represent surfaces as triangle meshes and build a differentiable rendering pipeline around triangle rasterization and neural shading. The renderer is used in a gradient descent optimization where both a triangle mesh and a neural shader are jointly optimized to reproduce the multi-view images. We evaluate our method on a public 3D reconstruction dataset and show that it can match the reconstruction accuracy of traditional baselines and neural approaches while surpassing them in optimization runtime. Additionally, we investigate the shader and find that it learns an interpretable representation of appearance, enabling applications such as 3D material editing.