IPVNet: Learning Implicit Point-Voxel Features for Open-Surface 3D Reconstruction
This work addresses a specific challenge in computer vision for applications requiring accurate 3D modeling of open surfaces, representing an incremental improvement over existing unsigned implicit methods.
The paper tackles the problem of reconstructing 3D open surfaces (e.g., non-watertight meshes) by proposing IPVNet, a learning-based implicit point-voxel model that predicts unsigned distances to avoid artifacts like artificial closing of gaps. Experiments on synthetic and real-world datasets show that IPVNet outperforms state-of-the-art methods and produces far fewer outliers in reconstructions.
Reconstruction of 3D open surfaces (e.g., non-watertight meshes) is an underexplored area of computer vision. Recent learning-based implicit techniques have removed previous barriers by enabling reconstruction in arbitrary resolutions. Yet, such approaches often rely on distinguishing between the inside and outside of a surface in order to extract a zero level set when reconstructing the target. In the case of open surfaces, this distinction often leads to artifacts such as the artificial closing of surface gaps. However, real-world data may contain intricate details defined by salient surface gaps. Implicit functions that regress an unsigned distance field have shown promise in reconstructing such open surfaces. Nonetheless, current unsigned implicit methods rely on a discretized representation of the raw data. This not only bounds the learning process to the representation's resolution, but it also introduces outliers in the reconstruction. To enable accurate reconstruction of open surfaces without introducing outliers, we propose a learning-based implicit point-voxel model (IPVNet). IPVNet predicts the unsigned distance between a surface and a query point in 3D space by leveraging both raw point cloud data and its discretized voxel counterpart. Experiments on synthetic and real-world public datasets demonstrates that IPVNet outperforms the state of the art while producing far fewer outliers in the resulting reconstruction.