ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images
This addresses the challenge of reconstructing 3D scenes from blurry images for applications like robotics or photography, but it is incremental as it builds on radiance fields with efficiency improvements.
The authors tackled the problem of novel view synthesis from extreme motion blurred images by developing ExBluRF, which jointly optimizes sharp radiance fields and camera trajectories, resulting in sharper 3D scenes with 10 times less training time and GPU memory consumption compared to existing methods.
We present ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization. Our approach consists of two main components: 6-DOF camera trajectory-based motion blur formulation and voxel-based radiance fields. From extremely blurred images, we optimize the sharp radiance fields by jointly estimating the camera trajectories that generate the blurry images. In training, multiple rays along the camera trajectory are accumulated to reconstruct single blurry color, which is equivalent to the physical motion blur operation. We minimize the photo-consistency loss on blurred image space and obtain the sharp radiance fields with camera trajectories that explain the blur of all images. The joint optimization on the blurred image space demands painfully increasing computation and resources proportional to the blur size. Our method solves this problem by replacing the MLP-based framework to low-dimensional 6-DOF camera poses and voxel-based radiance fields. Compared with the existing works, our approach restores much sharper 3D scenes from challenging motion blurred views with the order of 10 times less training time and GPU memory consumption.