CuriGS: Curriculum-Guided Gaussian Splatting for Sparse View Synthesis

TL;DR

CuriGS introduces a curriculum-guided approach for sparse-view 3D scene reconstruction with Gaussian Splatting, improving rendering quality and geometric consistency by progressively augmenting training views with a novel student-teacher framework.

Contribution

The paper proposes a curriculum-based method that generates and selects pseudo-views to enhance sparse-view 3D reconstruction using Gaussian Splatting, addressing overfitting and supervision scarcity.

Findings

Outperforms state-of-the-art in rendering fidelity

Achieves better geometric consistency

Effective in both synthetic and real scenes

Abstract

3D Gaussian Splatting (3DGS) has recently emerged as an efficient, high-fidelity representation for real-time scene reconstruction and rendering. However, extending 3DGS to sparse-view settings remains challenging because of supervision scarcity and overfitting caused by limited viewpoint coverage. In this paper, we present CuriGS, a curriculum-guided framework for sparse-view 3D reconstruction using 3DGS. CuriGS addresses the core challenge of sparse-view synthesis by introducing student views: pseudo-views sampled around ground-truth poses (teacher). For each teacher, we generate multiple groups of student views with different perturbation levels. During training, we follow a curriculum schedule that gradually unlocks higher perturbation level, randomly sampling candidate students from the active level to assist training. Each sampled student is regularized via depth-correlation and co-regularization, and evaluated using a multi-signal metric that combines SSIM, LPIPS, and an image-quality measure. For every teacher and perturbation level, we periodically retain the best-performing students and promote those that satisfy a predefined quality threshold to the training set, resulting in a stable augmentation of sparse training views. Experimental results show that CuriGS outperforms state-of-the-art baselines in both rendering fidelity and geometric consistency across various synthetic and real sparse-view scenes. Project page: https://zijian1026.github.io/CuriGS/