SurRF: Unsupervised Multi-View Stereopsis by Learning Surface Radiance Field

Citations of this article
Mendeley users who have this article in their library.
Get full text


The recent success in supervised multi-view stereopsis (MVS) relies on the onerously collected real-world 3D data. While the latest differentiable rendering techniques enable unsupervised MVS, they are restricted to discretized (e.g., point cloud) or implicit geometric representation, suffering from either low integrity for a textureless region or less geometric details for complex scenes. In this paper, we propose SurRF, an unsupervised MVS pipeline by learning Surface Radiance Field, i.e., a radiance field defined on a continuous and explicit 2D surface. Our key insight is that, in a local region, the explicit surface can be gradually deformed from a continuous initialization along view-dependent camera rays by differentiable rendering. That enables us to define the radiance field only on a 2D deformable surface rather than in a dense volume of 3D space, leading to compact representation while maintaining complete shape and realistic texture for large-scale complex scenes. We experimentally demonstrate that the proposed SurRF produces competitive results over the-state-of-The-Art on various real-world challenging scenes, without any 3D supervision. Moreover, SurRF shows great potential in owning the joint advantages of mesh (scene manipulation), continuous surface (high geometric resolution), and radiance field (realistic rendering).




Zhang, J., Ji, M., Wang, G., Xue, Z., Wang, S., & Fang, L. (2022). SurRF: Unsupervised Multi-View Stereopsis by Learning Surface Radiance Field. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7912–7927.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free