Camera-Agnostic Pruning of 3D Gaussian Splats via Descriptor-Based Beta Evidence
This addresses the need for efficient splat pruning in camera-agnostic exchange settings, offering a practical alternative to existing camera-dependent strategies, though it appears incremental as it builds on prior pruning concepts.
The paper tackles the problem of pruning 3D Gaussian splats to reduce complexity for efficient storage and processing, proposing a camera-agnostic method that achieves substantial pruning while preserving reconstruction quality, as demonstrated on standardized test sequences.
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.