Robust Fundamental Matrix Estimation from Single Image Motion Blur
For computer vision researchers, this work opens a new capability—extracting 3D motion from a single blurry image—but the method is incremental, adapting existing estimation techniques to handle ambiguous correspondences.
This paper introduces a method to estimate a fundamental matrix from a single motion-blurred image, enabling recovery of 3D camera motion during exposure. The approach handles time-direction ambiguous correspondences and incorporates uncertainty in smear pattern prediction, achieving robust estimation on synthetic and real datasets.
In this paper, we introduce a challenging task: extracting a fundamental matrix from a single motion blurred image. For a camera moving in 3D during exposure, the smear paths in the blurry image contain cues and constraints on this motion. We demonstrate the feasibility of establishing correspondences between two time instances within the camera exposure window, and that these can be used to robustly infer a fundamental matrix, which summarizes the motion of the camera during the exposure time. The inferred fundamental matrix is unique up to a transpose, corresponding to an ambiguity of the direction of time. Due to this per-smear ambiguity, classic methods, such as the 8-point algorithm, are no longer usable. The proposed method modifies the estimation to work on time-direction ambiguous correspondences. To improve the robustness of the fundamental matrix estimation, we also propose to incorporate an uncertainty measurement in smear pattern prediction and use it in the sampling process of the estimator. Experiments on synthetic and real-world motion-blur datasets demonstrate that our approach is able to estimate the fundamental matrix encoding the 3D camera motion, from single frames. Practical applicability is demonstrated on the downstream task of motion segmentation.