BAGS: Blur Agnostic Gaussian Splatting through Multi-Scale Kernel Modeling

TL;DR

This paper introduces BAGS, a novel method that enhances Gaussian Splatting for scene reconstruction and view synthesis in blurry images by modeling blur with per-pixel kernels and a quality mask, improving robustness and rendering quality.

Contribution

BAGS adds a 2D blur modeling component with a per-pixel kernel estimation and a quality mask, enabling robust scene reconstruction from blurry images, which was not addressed in prior Gaussian Splatting methods.

Findings

BAGS outperforms existing methods in photorealistic rendering under various blur conditions.

The proposed kernel optimization scheme is fast and avoids sub-optimal solutions.

BAGS maintains high-quality scene reconstruction despite image degradations.

Abstract

Recent efforts in using 3D Gaussians for scene reconstruction and novel view synthesis can achieve impressive results on curated benchmarks; however, images captured in real life are often blurry. In this work, we analyze the robustness of Gaussian-Splatting-based methods against various image blur, such as motion blur, defocus blur, downscaling blur, \etc. Under these degradations, Gaussian-Splatting-based methods tend to overfit and produce worse results than Neural-Radiance-Field-based methods. To address this issue, we propose Blur Agnostic Gaussian Splatting (BAGS). BAGS introduces additional 2D modeling capacities such that a 3D-consistent and high quality scene can be reconstructed despite image-wise blur. Specifically, we model blur by estimating per-pixel convolution kernels from a Blur Proposal Network (BPN). BPN is designed to consider spatial, color, and depth variations of the scene to maximize modeling capacity. Additionally, BPN also proposes a quality-assessing mask, which indicates regions where blur occur. Finally, we introduce a coarse-to-fine kernel optimization scheme; this optimization scheme is fast and avoids sub-optimal solutions due to a sparse point cloud initialization, which often occurs when we apply Structure-from-Motion on blurry images. We demonstrate that BAGS achieves photorealistic renderings under various challenging blur conditions and imaging geometry, while significantly improving upon existing approaches.