Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Peter Fasogbon, Ugurcan Budak, Patrice Rondao Alface, Hamed Rezazadegan Tavakoli

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.

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

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.
Paper Structure (26 sections, 9 equations, 3 figures, 2 tables)

This paper contains 26 sections, 9 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Pruning in 3DGS
  4. Training-Stage Pruning.
  5. Gradient-Based and Learned Pruning.
  6. Post-Training Compression Pipelines.
  7. Structural and Feature-Space Pruning.
  8. NeRF and Visibility-Based Pruning.
  9. Intrinsic Cues from Local Structure
  10. Positioning of This Work
  11. Proposed Method
  12. Local Descriptor Extraction using HSFH
  13. Geometric component.
  14. Appearance component from spherical harmonics.
  15. Optional view-aware features.
  16. ...and 11 more sections

Figures (3)

  • Figure 1: Overview of the proposed Gaussian splat pruning method on an example scene from the ISO/IEC MPEG CTC dataset mpegdatasets, rendered from a fixed camera viewpoint. The image columns show the non-pruned baseline and increasing pruning thresholds $\tau=0.1, 0.3, 0.50,$ and $0.7$, which remove about $10\%$, $30\%$, $50\%$, and $70\%$ of splats, respectively.
  • Figure 2: Method overview of the proposed camera-agnostic Gaussian splat pruning framework. Given trained 3D Gaussian splats, local descriptor statistics are computed and transformed into Beta-distributed evidence to model confidence and uncertainty. A one-shot confidence-aware ranking then removes redundant splats, balancing expected pruning likelihood and uncertainty to produce the final pruned representation.
  • Figure 3: Qualitative comparison of camera-agnostic pruning on three MPEG CTC scenes (bartender (tracked), breakfast (tracked), cinema (tracked)) at approximately 20% pruning. The columns show (left to right) the input rendering, descriptor-only pruning without Beta modelling (No Beta), and uncertainty-aware pruning with Beta evidence (Beta). Incorporating Beta evidence improves preservation of fine structures and reduces visible pruning artefacts.