Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations

Lu Sang, Maolin Gao, Abhishek Saroha, Daniel Cremers

Keywords: Neural implicits, SDF, surface reconstruction

Abstract: Neural implicits are a widely used surface presentation because they offer an adaptive resolution and support arbitrary topology changes. While previous works rely on ground truth point clouds or meshes, they often do not discuss the data acquisition and ignore the effect of input quality and sampling methods during reconstruction. In this paper, we introduce a sampling method with an uncertainty-augmented surface implicit representation that employs a sampling technique that considers the geometric characteristics of inputs. To this end, we introduce a strategy that efficiently computes differentiable geometric features, namely, mean curvatures, to guide the sampling phase during the training period. The uncertainty augmentation offers insights into the occupancy and reliability of the output signed distance value, thereby expanding representation capabilities into open surfaces. Finally, we demonstrate that our method improves the reconstruction of both synthetic and real-world data.

Submission Number: 13