DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting
This addresses the issue of spurious surfaces in 3D geometry reconstruction for computer vision and graphics applications, representing a novel method for a known bottleneck.
The paper tackled the problem of inaccurate 3D reconstructions with spurious surfaces in neural implicit surface fitting by proposing DiffCD, a symmetric differentiable Chamfer distance loss, which substantially outperformed existing methods across varying surface complexity and noise levels.
Neural implicit surfaces can be used to recover accurate 3D geometry from imperfect point clouds. In this work, we show that state-of-the-art techniques work by minimizing an approximation of a one-sided Chamfer distance. This shape metric is not symmetric, as it only ensures that the point cloud is near the surface but not vice versa. As a consequence, existing methods can produce inaccurate reconstructions with spurious surfaces. Although one approach against spurious surfaces has been widely used in the literature, we theoretically and experimentally show that it is equivalent to regularizing the surface area, resulting in over-smoothing. As a more appealing alternative, we propose DiffCD, a novel loss function corresponding to the symmetric Chamfer distance. In contrast to previous work, DiffCD also assures that the surface is near the point cloud, which eliminates spurious surfaces without the need for additional regularization. We experimentally show that DiffCD reliably recovers a high degree of shape detail, substantially outperforming existing work across varying surface complexity and noise levels. Project code is available at https://github.com/linusnie/diffcd.