Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
This addresses the problem of accurate 3D reconstruction from multiple views for applications in computer vision and graphics, representing an incremental improvement over existing methods.
The paper tackles multiview 3D surface reconstruction by introducing a neural network that learns geometry, camera parameters, and a neural renderer from 2D images, achieving state-of-the-art results with high fidelity and detail on the DTU MVS dataset.
In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates the light reflected from the surface towards the camera. The geometry is represented as a zero level-set of a neural network, while the neural renderer, derived from the rendering equation, is capable of (implicitly) modeling a wide set of lighting conditions and materials. We trained our network on real world 2D images of objects with different material properties, lighting conditions, and noisy camera initializations from the DTU MVS dataset. We found our model to produce state of the art 3D surface reconstructions with high fidelity, resolution and detail.