Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting

TL;DR

This paper presents a fast, training-free method for feature field rendering in 3D Gaussian splatting that achieves high-quality 2D and 3D segmentation results without the need for training or post-processing.

Contribution

It introduces a novel gradient-weighted feature back-projection technique that replaces training-based methods for efficient 3D Gaussian splatting.

Findings

Achieves high-quality 2D and 3D segmentation without training.

Offers a fast, scalable alternative to training-based feature distillation.

Performs comparably to training-based methods in experiments.

Abstract

We introduce a training-free method for feature field rendering in Gaussian splatting. Our approach back-projects 2D features into pre-trained 3D Gaussians, using a weighted sum based on each Gaussian's influence in the final rendering. While most training-based feature field rendering methods excel at 2D segmentation but perform poorly at 3D segmentation without post-processing, our method achieves high-quality results in both 2D and 3D segmentation. Experimental results demonstrate that our approach is fast, scalable, and offers performance comparable to training-based methods.