GeMS: 用于极端运动模糊的高效高斯溅射
GeMS: Efficient Gaussian Splatting for Extreme Motion Blur
AI总结：
针对现有3D高斯溅射方法处理极端运动模糊需依赖清晰图像或因特征不可靠失败的问题，提出GeMS框架，通过VGGSfM、3DGS-MCMC及联合优化直接从模糊图像重建，还提出GeMS-E结合事件去模糊细化，在合成和真实数据集上取得SOTA性能。
摘要：
我们提出GeMS，这是一个专为处理严重运动模糊图像设计的3D高斯溅射（3DGS）框架。针对极端模糊的最先进去模糊方法（如ExBluRF）以及基于高斯溅射的方法（如Deblur-GS）通常假设可获取清晰图像以进行相机姿态估计和点云生成，这是一个不现实的假设。依赖COLMAP初始化的方法（如BAD-Gaussians）也因严重模糊下特征对应不可靠而失败。为应对这些挑战，我们提出GeMS，一个直接从极端模糊图像重建场景的3DGS框架。GeMS集成：（1）VGGSfM，一个基于深度学习的运动恢复结构（Structure-from-Motion）管线，可直接从模糊输入估计姿态并生成点云；（2）3DGS-MCMC，通过将高斯视为概率分布的样本实现稳健的场景初始化，消除启发式的 densification 和 pruning；（3）相机轨迹与高斯参数的联合优化，以实现稳定重建。虽然该管线产生了良好结果，但当所有输入都严重模糊时仍可能存在不准确。为缓解这一问题，我们提出GeMS-E，它集成了使用事件的渐进式细化步骤：（4）基于事件的双积分（EDI）去模糊恢复更清晰的图像，然后将其输入GeMS，从而改进姿态估计、点云生成和整体重建。GeMS和GeMS-E在合成和真实世界数据集上均实现了最先进的性能。据我们所知，这是首个直接从严重模糊输入中在3DGS内解决极端运动模糊的框架。
英文摘要：
We introduce GeMS, a framework for 3D Gaussian Splatting (3DGS) designed to handle severely motion-blurred images. State-of-the-art deblurring methods for extreme blur, such as ExBluRF, as well as Gaussian Splatting-based approaches like Deblur-GS, typically assume access to sharp images for camera pose estimation and point cloud generation, an unrealistic assumption. Methods relying on COLMAP initialization, such as BAD-Gaussians, also fail due to unreliable feature correspondences under severe blur. To address these challenges, we propose GeMS, a 3DGS framework that reconstructs scenes directly from extremely blurred images. GeMS integrates: (1) VGGSfM, a deep learning-based Structure-from-Motion pipeline that estimates poses and generates point clouds directly from blurred inputs; (2) 3DGS-MCMC, which enables robust scene initialization by treating Gaussians as samples from a probability distribution, eliminating heuristic densification and pruning; and (3) joint optimization of camera trajectories and Gaussian parameters for stable reconstruction. While this pipeline produces strong results, inaccuracies may remain when all inputs are severely blurred. To mitigate this, we propose GeMS-E, which integrates a progressive refinement step using events: (4) Event-based Double Integral (EDI) deblurring restores sharper images that are then fed into GeMS, improving pose estimation, point cloud generation, and overall reconstruction. Both GeMS and GeMS-E achieve state-of-the-art performance on synthetic and real-world datasets. To our knowledge, this is the first framework to address extreme motion blur within 3DGS directly from severely blurred inputs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
