图像即IMU：从单张运动模糊图像中估计相机运动

Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image

March 21, 2025

作者: Jerred Chen, Ronald Clark

cs.AI

摘要

在众多机器人及虚拟/增强现实应用中，快速相机运动导致严重的运动模糊，使得现有相机姿态估计方法失效。本研究中，我们提出了一种创新框架，将运动模糊视为运动估计的丰富线索，而非需要消除的干扰。我们的方法通过直接从单张运动模糊图像预测密集运动流场和单目深度图来实现。随后，在小运动假设下，通过求解线性最小二乘问题恢复瞬时相机速度。本质上，我们的方法生成了一种类似IMU的测量值，能够稳健捕捉快速且剧烈的相机运动。为训练模型，我们构建了一个大规模数据集，其中包含基于ScanNet++v2生成的逼真合成运动模糊，并通过使用完全可微分的管道在真实数据上进行端到端训练，进一步优化模型。在现实世界基准上的广泛评估表明，我们的方法在角速度和线速度估计上达到了业界领先水平，超越了如MASt3R和COLMAP等现有方法。

English

In many robotics and VR/AR applications, fast camera motions cause a high level of motion blur, causing existing camera pose estimation methods to fail. In this work, we propose a novel framework that leverages motion blur as a rich cue for motion estimation rather than treating it as an unwanted artifact. Our approach works by predicting a dense motion flow field and a monocular depth map directly from a single motion-blurred image. We then recover the instantaneous camera velocity by solving a linear least squares problem under the small motion assumption. In essence, our method produces an IMU-like measurement that robustly captures fast and aggressive camera movements. To train our model, we construct a large-scale dataset with realistic synthetic motion blur derived from ScanNet++v2 and further refine our model by training end-to-end on real data using our fully differentiable pipeline. Extensive evaluations on real-world benchmarks demonstrate that our method achieves state-of-the-art angular and translational velocity estimates, outperforming current methods like MASt3R and COLMAP.