SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting

TL;DR

SuperGS introduces a two-stage coarse-to-fine framework with multi-view consistency and uncertainty modeling to enhance high-resolution 3D scene reconstruction from low-resolution inputs, outperforming existing methods.

Contribution

It presents a novel multi-view densification and uncertainty-guided refinement approach for high-resolution 3D scene reconstruction, extending Gaussian Splatting techniques.

Findings

SuperGS achieves superior quality in high-resolution scene reconstruction.

It outperforms state-of-the-art HRNVS methods on multiple datasets.

The method maintains multi-view consistency and detailed scene fidelity.

Abstract

Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the coarse nature of primitives derived from low-resolution input views. To address this issue, we propose SuperGS, an expansion of Scaffold-GS designed with a two-stage coarse-to-fine training framework. In the low-resolution stage, we introduce a latent feature field to represent the low-resolution scene, which serves as both the initialization and foundational information for super-resolution optimization. In the high-resolution stage, we propose a multi-view consistent densification strategy that backprojects high-resolution depth maps based on error maps and employs a multi-view voting mechanism, mitigating ambiguities caused by multi-view inconsistencies in the pseudo labels provided by 2D prior models while avoiding Gaussian redundancy. Furthermore, we model uncertainty through variational feature learning and use it to guide further scene representation refinement and adjust the supervisory effect of pseudo-labels, ensuring consistent and detailed scene reconstruction. Extensive experiments demonstrate that SuperGS outperforms state-of-the-art HRNVS methods on both forward-facing and 360-degree datasets.