仅用一张模糊图像和事件流，重建清晰3D场景与相机运动
BeSplat: Gaussian Splatting from a Single Blurry Image and Event Stream
- 联合优化高斯点云与贝塞尔相机运动模型
- 在真实和合成数据上实现视图一致的清晰渲染
- 首次将事件流用于高斯点云的单图重建
新视角合成因辐射场方法而大幅提升。3D高斯点云（3DGS）有效解决了神经辐射场（NeRF）训练耗时长、渲染慢等问题，同时保持高质量重建。本文提出BeSplat，从单张运动模糊图像及其对应的事件流中恢复清晰的辐射场（高斯点云）。方法通过3DGS联合学习场景表示，并利用贝塞尔SE(3)参数化有效估计相机运动，最小化合成图像与真实模糊图像及事件流之间的差异。我们在合成与真实数据集上评估该方法，结果表明可从学习到的辐射场和估计的相机轨迹中生成视图一致且清晰的图像。据我们所知，这是首个在高斯点云框架下，结合事件流时间信息解决此高度病态问题的工作。
原文摘要 · Abstract (English)
Novel view synthesis has been greatly enhanced by the development of radiance field methods. The introduction of 3D Gaussian Splatting (3DGS) has effectively addressed key challenges, such as long training times and slow rendering speeds, typically associated with Neural Radiance Fields (NeRF), while maintaining high-quality reconstructions. In this work (BeSplat), we demonstrate the recovery of sharp radiance field (Gaussian splats) from a single motion-blurred image and its corresponding event stream. Our method jointly learns the scene representation via Gaussian Splatting and recovers the camera motion through Bezier SE(3) formulation effectively, minimizing discrepancies between synthesized and real-world measurements of both blurry image and corresponding event stream. We evaluate our approach on both synthetic and real datasets, showcasing its ability to render view-consistent, sharp images from the learned radiance field and the estimated camera trajectory. To the best of our knowledge, ours is the first work to address this highly challenging ill-posed problem in a Gaussian Splatting framework with the effective incorporation of temporal information captured using the event stream.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。