ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images

TL;DR

ExBluRF is a new method that efficiently reconstructs sharp 3D scenes from extreme motion blurred images by jointly estimating camera trajectories and radiance fields, significantly reducing computational resources.

Contribution

It introduces a voxel-based radiance field approach combined with 6-DOF camera trajectory estimation to handle extreme motion blur efficiently.

Findings

Restores sharper 3D scenes from blurred images.

Achieves 10x reduction in training time and GPU memory.

Effectively models physical motion blur with joint optimization.

Abstract

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.