# How Powerful Are Randomly Initialized Pointcloud Set Functions?

arXiv: https://arxiv.org/abs/2003.05410 · HTML: https://mlsanity.com/paper/2003.05410/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining](https://mlsanity.com/paper/2312.09249/) (2023)
- [Robust Point Cloud Processing through Positional Embedding](https://mlsanity.com/paper/2309.00339/) (2023)
- [Random Embeddings and Linear Regression can Predict Protein Function](https://mlsanity.com/paper/2104.14661/) (2021)

## Abstract (arXiv)

We study random embeddings produced by untrained neural set functions, and show that they are powerful representations which well capture the input features for downstream tasks such as classification, and are often linearly separable. We obtain surprising results that show that random set functions can often obtain close to or even better accuracy than fully trained models. We investigate factors that affect the representative power of such embeddings quantitatively and qualitatively.