IE-SRGS: An Internal-External Knowledge Fusion Framework for High-Fidelity 3D Gaussian Splatting Super-Resolution

TL;DR

The paper introduces IE-SRGS, a novel framework that combines external 2D super-resolution priors with internal 3D Gaussian features to improve high-fidelity 3D Gaussian Splatting super-resolution, addressing cross-view inconsistencies and domain gaps.

Contribution

It proposes a joint external-internal knowledge fusion approach with a mask-guided strategy for high-quality 3D super-resolution, outperforming existing methods.

Findings

Outperforms state-of-the-art methods in accuracy and visual quality

Effectively addresses cross-view inconsistency issues

Demonstrates robustness on synthetic and real-world data

Abstract

Reconstructing high-resolution (HR) 3D Gaussian Splatting (3DGS) models from low-resolution (LR) inputs remains challenging due to the lack of fine-grained textures and geometry. Existing methods typically rely on pre-trained 2D super-resolution (2DSR) models to enhance textures, but suffer from 3D Gaussian ambiguity arising from cross-view inconsistencies and domain gaps inherent in 2DSR models. We propose IE-SRGS, a novel 3DGS SR paradigm that addresses this issue by jointly leveraging the complementary strengths of external 2DSR priors and internal 3DGS features. Specifically, we use 2DSR and depth estimation models to generate HR images and depth maps as external knowledge, and employ multi-scale 3DGS models to produce cross-view consistent, domain-adaptive counterparts as internal knowledge. A mask-guided fusion strategy is introduced to integrate these two sources and synergistically exploit their complementary strengths, effectively guiding the 3D Gaussian optimization toward high-fidelity reconstruction. Extensive experiments on both synthetic and real-world benchmarks show that IE-SRGS consistently outperforms state-of-the-art methods in both quantitative accuracy and visual fidelity.