3D Gaussian Splatting (3DGS) enables photorealistic rendering but suffers from artefacts due to sparse Structure-from-Motion (SfM) initialisation. To address this limitation, we propose GP-GS, a Gaussian Process (GP) based densification framework for 3DGS optimisation. GP-GS formulates point cloud densification as a continuous regression problem, where a GP learns a local mapping from 2D pixel coordinates to 3D position and colour attributes. An adaptive neighbourhood-based sampling strategy generates candidate pixels for inference, while GP-predicted uncertainty is used to filter unreliable predictions, reducing noise and preserving geometric structure. Extensive experiments on synthetic and real-world benchmarks demonstrate that GP-GS consistently improves reconstruction quality and rendering fidelity, achieving up to 1.12 dB PSNR improvement over strong baselines.
@article{arxiv.2502.02283,
title = {GP-GS: Gaussian Processes Densification for 3D Gaussian Splatting},
author = {Zhihao Guo and Jingxuan Su and Chenghao Qian and Shenglin Wang and Jinlong Fan and Jing Zhang and Wei Zhou and Hadi Amirpour and Yunlong Zhao and Liangxiu Han and Peng Wang},
journal= {arXiv preprint arXiv:2502.02283},
year = {2026}
}