# Geometry Aware Field-to-field Transformations for 3D Semantic Segmentation

Source: [Geometry Aware Field-to-field Transformations for 3D Semantic Segmentation](<https://www.sota2.com/research/paper/68fa70cb1e209131cea4d29f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:49:52.893Z

Authors: Dominik Hollidt, Clinton Wang, Polina Golland, Marc Pollefeys

Published: 2023-10-08T11:48:19.000Z

## Abstract

We present a novel approach to perform 3D semantic segmentation solely from 2D supervision by leveraging Neural Radiance Fields (NeRFs). By extracting features along a surface point cloud, we achieve a compact representation of the scene which is sample-efficient and conducive to 3D reasoning. Learning this feature space in an unsupervised manner via masked autoencoding enables few-shot segmentation. Our method is agnostic to the scene parameterization, working on scenes fit with any type of NeRF.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.05133>)

[PDF](<https://arxiv.org/pdf/2310.05133.pdf>)