Convolutional Neural Network-based Efficient Dense Point Cloud Generation using Unsigned Distance Fields
This addresses a crucial problem in 3D computer vision and graphics for applications requiring efficient and high-quality point cloud generation, though it is incremental as it builds on implicit function learning.
The paper tackles the problem of generating dense point clouds from sparse or incomplete inputs, which is challenging due to computational expense, limited resolution, and restrictions to watertight surfaces. The result is a lightweight Convolutional Neural Network that outperforms state-of-the-art methods with 7.8x fewer parameters, 2.4x faster inference, and up to 24.8% improved quality.
Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from limited resolution, or both. In addition, some methods are strictly limited to watertight surfaces -- another major obstacle for a number of applications. To address these issues, we propose a lightweight Convolutional Neural Network that learns and predicts the unsigned distance field for arbitrary 3D shapes for dense point cloud generation using the recently emerged concept of implicit function learning. Experiments demonstrate that the proposed architecture outperforms the state of the art by 7.8x less model parameters, 2.4x faster inference time and up to 24.8% improved generation quality compared to the state-of-the-art.