RPINet: Urban Point Cloud and Remote Sensing Image Fusion for Semantic Segmentation

A dataset likely containing results or supporting data for the RPINet model, which integrates 2D remote sensing images with 3D point cloud data for urban scene understanding. The data was created by Zhe Jing and last updated on May 22, 2026. The dataset is small, at 5.5 KB, and is stored in an XLS file format.

Use Cases

• Benchmarking semantic segmentation models based on the reported 66.5% mean IoU metric.
• Studying the fusion of 2D image texture and 3D geometric features for urban analysis.
• Evaluating adaptive sampling strategies for processing large-scale, irregularly distributed point clouds.

Strengths

• Dataset is associated with a model achieving a reported 66.5% mean IoU on the SensatUrban benchmark.
• Data is licensed under CC-BY-4.0, allowing for open sharing and modification.
• The associated research describes a specific hybrid attention-based fusion module for multimodal data.

Limitations

• The dataset is very small (5.5 KB), suggesting it may contain only summary results or metadata, not the full point cloud or image data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare

Collection Method

Likely generated as part of the RPINet research for semantic segmentation of urban scenes.

Freshness

Last updated 2026-05-22 17:38:43; freshness should be verified.