# Tabulated MLP for Fast Point Feature Embedding

arXiv: https://arxiv.org/abs/1912.00790 · HTML: https://mlsanity.com/paper/1912.00790/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2019.

## Built on by (most cited first, 2 of 2)

- [Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fields](https://mlsanity.com/paper/2309.06030/) (2023)
- [3D Gaussian Point Encoders](https://mlsanity.com/paper/2511.04797/) (2025)

## Abstract (arXiv)

Aiming at a drastic speedup for point-data embeddings at test time, we propose a new framework that uses a pair of multi-layer perceptron (MLP) and look-up table (LUT) to transform point-coordinate inputs into high-dimensional features. When compared with PointNet's feature embedding part realized by MLP that requires millions of dot products, ours at test time requires no such layers of matrix-vector products but requires only looking up the nearest entities followed by interpolation, from the tabulated MLP defined over discrete inputs on a 3D lattice. We call this framework as "LUTI-MLP: LUT Interpolation MLP" that provides a way to train end-to-end tabulated MLP coupled to a LUT in a specific manner without the need for any approximation at test time. LUTI-MLP also provides significant speedup for Jacobian computation of the embedding function wrt global pose coordinate on Lie algebra mathfrakse(3) at test time, which could be used for point-set registration problems. After extensive architectural analysis using ModelNet40 dataset, we confirmed that our LUTI-MLP even with a small-sized table (8× 8× 8) yields performance comparable to that of MLP while achieving significant speedup: 80× for embedding, 12× for approximate Jacobian, and 860× for canonical Jacobian.