Bootstrap-GS: Self-Supervised Augmentation for High-Fidelity Gaussian Splatting
This addresses a critical limitation in 3D reconstruction for rendering applications, though it appears incremental as it builds directly on existing 3D-GS methods.
The paper tackles the problem of training sampling deficiency in 3D Gaussian Splatting, which causes artifacts like dilation and aliasing in novel views, by introducing a bootstrapping framework that synthesizes pseudo-ground truth from novel views and reintegrates them into training, resulting in reduced artifacts and improved quantitative metrics.
Recent advancements in 3D Gaussian Splatting (3D-GS) have established new benchmarks for rendering quality and efficiency in 3D reconstruction. However, 3D-GS faces critical limitations when generating novel views that significantly deviate from those encountered during training. Moreover, issues such as dilation and aliasing arise during zoom operations. These challenges stem from a fundamental issue: training sampling deficiency. In this paper, we introduce a bootstrapping framework to address this problem. Our approach synthesizes pseudo-ground truth from novel views that align with the limited training set and reintegrates these synthesized views into the training pipeline. Experimental results demonstrate that our bootstrapping technique not only reduces artifacts but also improves quantitative metrics. Furthermore, our technique is highly adaptable, allowing various Gaussian-based method to benefit from its integration.