# GS-MSDR: Gaussian Splatting with Multi-Scale Deblurring and Resolution Enhancement

## TL;DR

This paper introduces GS-MSDR, a new method that improves 3D scene reconstruction by handling multiple types of image blur and enhancing resolution.

## Contribution

GS-MSDR introduces a novel framework combining multi-scale deblurring and resolution enhancement for 3D Gaussian Splatting.

## Key findings

- GS-MSDR outperforms existing methods in deblurring and 3D reconstruction under complex degradation scenarios.
- The proposed MAAN and HPKO modules effectively recover fine details and reduce ambiguity in degraded regions.
- The method achieves efficient rendering while maintaining high accuracy in the 3DGS framework.

## Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable performance in scene reconstruction and novel view synthesis on benchmark datasets. However, real-world images are frequently affected by degradations such as camera shake, object motion, and lens defocus, which not only compromise image quality but also severely hinder the accuracy of 3D reconstruction—particularly in fine details. While existing deblurring approaches have made progress, most are limited to addressing a single type of blur, rendering them inadequate for complex scenarios involving multiple blur sources and resolution degradation. To address these challenges, we propose Gaussian Splatting with Multi-Scale Deblurring and Resolution Enhancement (GS-MSDR), a novel framework that seamlessly integrates multi-scale deblurring and resolution enhancement. At its core, our Multi-scale Adaptive Attention Network (MAAN) fuses multi-scale features to enhance image information, while the Multi-modal Context Adapter (MCA) and adaptive spatial pooling modules further refine feature representation, facilitating the recovery of fine details in degraded regions. Additionally, our Hierarchical Progressive Kernel Optimization (HPKO) method mitigates ambiguity and ensures precise detail reconstruction through layer-wise optimization. Extensive experiments demonstrate that GS-MSDR consistently outperforms state-of-the-art methods under diverse degraded scenarios, achieving superior deblurring, accurate 3D reconstruction, and efficient rendering within the 3DGS framework.