Blur Robust Optical Flow using Motion Channel
This work addresses the challenge of optical flow estimation in blurry videos, which is crucial for applications like robotics and video analysis, but it appears incremental as it builds on existing methods by adding a motion channel.
The paper tackles the problem of estimating optical flow in real-world videos with motion blur by introducing a hybrid framework that integrates camera motion data from a 3D pose sensor with an RGB camera, resulting in improved accuracy compared to three state-of-the-art baselines on proposed ground truth blurry sequences and real-world footage.
It is hard to estimate optical flow given a realworld video sequence with camera shake and other motion blur. In this paper, we first investigate the blur parameterization for video footage using near linear motion elements. we then combine a commercial 3D pose sensor with an RGB camera, in order to film video footage of interest together with the camera motion. We illustrates that this additional camera motion/trajectory channel can be embedded into a hybrid framework by interleaving an iterative blind deconvolution and warping based optical flow scheme. Our method yields improved accuracy within three other state-of-the-art baselines given our proposed ground truth blurry sequences; and several other realworld sequences filmed by our imaging system.