ARGP: Adaptive and Recoverable 3D Gaussian Splatting Pruning for Efficient Real-Time Scene Reconstruction

3D Gaussian Splatting (3DGS) has emerged as an efficient explicit representation for real-time novel view synthesis. However, repeated densification during training often leads to uncontrolled Gaussian growth, causing heavy memory overhead and slow convergence. This redundancy stems from two limitations: (1) opacity-based sparsification that fails to maintain consistent pruning pressure under evolving distributions; (2) irreversible pruning strategies that risk eliminating essential Gaussians. To address these, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Adaptive and Recoverable Gaussian Pruning (ARGP)</i>, a training-integrated framework that suppresses redundant growth while preserving reconstruction quality. During densification, we employ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Adaptive Opacity Pruning (AOP)</i>, which removes a fixed proportion of low-opacity Gaussians based on quantiles, effectively suppressing redundancy. In the fine-tuning stage, we introduce <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Iterative Recovery Pruning (IRP)</i>, which selectively reinstates critical Gaussians using a gradient-informed recovery score, thus preventing over-pruning and preserving reconstruction quality. Extensive experimental results on Mip-NeRF 360, Tanks & Temples, and Deep Blending validate the effectiveness of our proposed ARGP. For instance, ARGP achieves a 90.2% reduction in Gaussian counts and a 1.33× training speedup, while maintaining competitive reconstruction quality on Mip-NeRF 360. Our code is available at https://github.com/Sinyo-Liu/ARGP.