Robust Fundamental Matrix Estimation from Single Image Motion Blur

TL;DR

This paper presents a novel method for estimating the fundamental matrix from a single motion-blurred image by leveraging smear patterns to infer camera motion, overcoming limitations of traditional approaches.

Contribution

It introduces a robust approach to extract the fundamental matrix from a single blurred image, incorporating uncertainty measurement and handling time-direction ambiguity.

Findings

Successfully estimates the fundamental matrix from synthetic and real motion-blurred images.

Demonstrates practical use in motion segmentation tasks.

Outperforms classic methods that require multiple images.

Abstract

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.