BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting

arXiv:2403.11831v1 Announce Type: new
Abstract: While neural rendering has demonstrated impressive capabilities in 3D scene reconstruction and novel view synthesis, it heavily relies on high-quality sharp images and accurate camera poses. Numerous approaches have been proposed to train Neural Radiance Fields (NeRF) with motion-blurred images, commonly encountered in real-world scenarios such as low-light or long-exposure conditions. However, the implicit representation of NeRF struggles to accurately recover intricate details from severely motion-blurred images and cannot achieve real-time rendering. In contrast, recent …

abstract arxiv capabilities cs.cv fields images light low nerf neural radiance fields neural rendering novel quality rendering synthesis train type view world