MSCD-GS：基于高斯泼溅的运动分离协同去模糊动态重建
MSCD-GS: Motion-Separated Cooperative Deblurring Dynamic Reconstruction via Gaussian Splatting
把曝光时间内的相机与物体运动分别建模为静态/动态高斯各自的运动模型，并用运动感知网络合成虚拟模糊图与去模糊网络结果协同监督，可直接迁移到任何用高斯泼溅做动态场景重建时处理运动模糊输入的流程。
原文依据 we designed motion-aware networks for static and dynamic Gaussians, thereby synthesizing virtual blurred images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管基于高斯泼溅的 4D 重建已取得许多令人瞩目的成果，但从普通单目相机拍摄的真实图像中进行重建仍是一项重大挑战。在动态场景中，由于相机与物体在曝光时间内发生运动，这些输入图像不可避免地包含大量运动模糊，严重损害了重建质量与新视角合成效果。现有的去模糊 3D 高斯模型仍无法处理真实动态场景中的运动模糊问题。为应对这些挑战，我们提出 MSCD-GS——一种基于高斯泼溅的运动分离协同去模糊 4D 重建新方法，能够有效处理运动模糊输入。具体而言，由于静态与动态高斯具有不同的运动特性，我们为动态场景重建分别建立独立的运动模型。为预测高斯在曝光时间内的变化，我们为静态与动态高斯设计了运动感知网络，从而合成虚拟模糊图像。最后，我们利用去模糊网络的结果与合成图像协同监督 4D 重建。大量实验表明，MSCD-GS 能够从模糊图像输入中有效重建高质量动态场景，性能优于现有方法。
英文原文摘要 1377 字符
Although 4D reconstruction based on Gaussian Splatting has achieved many impressive results, reconstructing real-world images captured by a casual monocular camera remains a significant challenge. In dynamic scenes, as the camera and objects move during the exposure time, these input images inevitably contain a considerable amount of motion blur, which severely compromises the quality of reconstruction and new viewpoint synthesis. The existing deblurring 3D Gaussian models still cannot handle motion blur issues in real dynamic scenes. To address these challenges, we propose MSCD-GS--a novel method for motion-separated collaborative deblurring 4D reconstruction via Gaussian Splatting, capable of effectively handling motion-blurred inputs. Specifically, due to the distinct motion characteristics of static and dynamic Gaussians, we perform separate motion models for dynamic scene reconstruction. To predict Gaussian changes over exposure time, we designed motion-aware networks for static and dynamic Gaussians, thereby synthesizing virtual blurred images. Finally, we utilize the results from the deblurring network and the synthesized images to supervise 4D reconstruction collaboratively. Extensive experiments demonstrate that MSCD-GS can effectively reconstruct high-quality dynamic scenes from blurred image inputs, with performance surpassing existing methods.