Timezone: »

Shape As Points: A Differentiable Poisson Solver
Songyou Peng · Max Jiang · Yiyi Liao · Michael Niemeyer · Marc Pollefeys · Andreas Geiger

Fri Dec 10 12:20 AM -- 12:35 AM (PST) @ None

In recent years, neural implicit representations gained popularity in 3D reconstruction due to their expressiveness and flexibility. However, the implicit nature of neural implicit representations results in slow inference times and requires careful initialization. In this paper, we revisit the classic yet ubiquitous point cloud representation and introduce a differentiable point-to-mesh layer using a differentiable formulation of Poisson Surface Reconstruction (PSR) which allows for a GPU-accelerated fast solution of the indicator function given an oriented point cloud. The differentiable PSR layer allows us to efficiently and differentiably bridge the explicit 3D point representation with the 3D mesh via the implicit indicator field, enabling end-to-end optimization of surface reconstruction metrics such as Chamfer distance. This duality between points and meshes hence allows us to represent shapes as oriented point clouds, which are explicit, lightweight and expressive. Compared to neural implicit representations, our Shape-As-Points (SAP) model is more interpretable, lightweight, and accelerates inference time by one order of magnitude. Compared to other explicit representations such as points, patches, and meshes, SAP produces topology-agnostic, watertight manifold surfaces. We demonstrate the effectiveness of SAP on the task of surface reconstruction from unoriented point clouds and learning-based reconstruction.

Author Information

Songyou Peng (ETH Zurich & MPI for Intelligent Systems)
Max Jiang (Waymo)
Yiyi Liao (University of Tübingen)
Michael Niemeyer (Max Planck for Intelligent Systems)
Marc Pollefeys (ETH Zurich)
Andreas Geiger (MPI-IS and University of Tuebingen)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors