Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos
This addresses the challenge of 3D reconstruction from blurry videos, which is important for computer vision applications like robotics and autonomous driving, but it is incremental as it builds on existing differentiable rendering techniques.
The paper tackles the problem of estimating 3D shape, motion, and appearance of motion-blurred objects from videos by modeling blur generatively with parameters like position, velocity, and bounces, using differentiable rendering to minimize reprojection error. It outperforms previous methods on benchmark datasets for deblurring and 3D reconstruction.
We propose a method for jointly estimating the 3D motion, 3D shape, and appearance of highly motion-blurred objects from a video. To this end, we model the blurred appearance of a fast moving object in a generative fashion by parametrizing its 3D position, rotation, velocity, acceleration, bounces, shape, and texture over the duration of a predefined time window spanning multiple frames. Using differentiable rendering, we are able to estimate all parameters by minimizing the pixel-wise reprojection error to the input video via backpropagating through a rendering pipeline that accounts for motion blur by averaging the graphics output over short time intervals. For that purpose, we also estimate the camera exposure gap time within the same optimization. To account for abrupt motion changes like bounces, we model the motion trajectory as a piece-wise polynomial, and we are able to estimate the specific time of the bounce at sub-frame accuracy. Experiments on established benchmark datasets demonstrate that our method outperforms previous methods for fast moving object deblurring and 3D reconstruction.