Camera-Agnostic Pruning of 3D Gaussian Splats via Descriptor-Based Beta Evidence

TL;DR

This paper introduces a camera-agnostic, one-shot pruning method for 3D Gaussian splats that uses attribute-based descriptors and a Beta evidence model to efficiently reduce complexity without relying on camera parameters.

Contribution

We propose a novel, camera-agnostic pruning approach using structural and appearance descriptors combined with a Beta evidence model for reliability estimation.

Findings

Achieves substantial pruning while maintaining reconstruction quality.

Operates effectively without camera parameters or view-dependent information.

Demonstrates generalizability on standardized test sequences.

Abstract

The pruning of 3D Gaussian splats is essential for reducing their complexity to enable efficient storage, transmission, and downstream processing. However, most of the existing pruning strategies depend on camera parameters, rendered images, or view-dependent measures. This dependency becomes a hindrance in emerging camera-agnostic exchange settings, where splats are shared directly as point-based representations (e.g., .ply). In this paper, we propose a camera-agnostic, one-shot, post-training pruning method for 3D Gaussian splats that relies solely on attribute-derived neighbourhood descriptors. As our primary contribution, we introduce a hybrid descriptor framework that captures structural and appearance consistency directly from the splat representation. Building on these descriptors, we formulate pruning as a statistical evidence estimation problem and introduce a Beta evidence model that quantifies per-splat reliability through a probabilistic confidence score. Experiments conducted on standardized test sequences defined by the ISO/IEC MPEG Common Test Conditions (CTC) demonstrate that our approach achieves substantial pruning while preserving reconstruction quality, establishing a practical and generalizable alternative to existing camera-dependent pruning strategies.