Rethinking Data Input for Point Cloud Upsampling
This addresses a fundamental methodological question in 3D reconstruction for researchers, though it appears incremental as it compares existing input types rather than introducing a new technique.
The paper investigated whether whole model inputs outperform patch-based inputs for point cloud upsampling, finding that patch-based inputs consistently performed better on PU1K and ABC datasets.
Point cloud upsampling is crucial for tasks like 3D reconstruction. While existing methods rely on patch-based inputs, and there is no research discussing the differences and principles between point cloud model full input and patch based input. Ergo, we propose a novel approach using whole model inputs i.e. Average Segment input. Our experiments on PU1K and ABC datasets reveal that patch-based inputs consistently outperform whole model inputs. To understand this, we will delve into factors in feature extraction, and network architecture that influence upsampling results.