Hypershadow: 3D Point Clouds of Ordinary Objects vs. Higher-Dimensional Projections

Hypershadow is a benchmark dataset designed to answer one specific question: given a 3D point cloud, can you tell if it is an ordinary 3D object or the 3D projection of an object from a higher spatial dimension. The dataset was created by AkshaySasi and was last updated on Hugging Face in July 2026. Label 1 clouds are projections of objects living in R^4, R^5, or R^6, including hyperspheres, tesseracts, and Clifford tori.

Use Cases

• Train classifiers to distinguish between 3D objects and higher-dimensional projections based on point cloud geometry.
• Benchmark the ability of neural networks to perceive latent geometric properties not directly observable in 3D.
• Study the representational limits of 3D point cloud models when confronted with data originating from higher-dimensional spaces.

Strengths

• Dataset is explicitly designed as a benchmark for a specific, novel research question in geometric perception.
• Includes projections of diverse higher-dimensional shapes such as hyperspheres, tesseracts, Clifford tori, duocylinders, and hypertori.

Limitations

• Column-level documentation and sample data are unavailable, making field semantics and data structure unclear.
• The dataset size, number of rows, and file formats are unknown, limiting suitability assessment.
• Last updated 2026-07-14 09:28:29; freshness should be verified.

Provenance

Source

huggingface

Collection Method

Likely generated through mathematical simulation of higher-dimensional objects and their 3D projections.

Freshness

Last updated 2026-07-14 09:28:29.