ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation
This addresses the need for motion analysis in applications like autonomous navigation when consecutive frames are unavailable, offering a novel solution to capture motion uncertainty without task-specific training.
The paper tackles the problem of single-image optical flow estimation by proposing ProbDiffFlow, a training-free framework that estimates probabilistic flow distributions from a single image, achieving superior accuracy, diversity, and efficiency in experiments on synthetic and real-world datasets.
This paper studies optical flow estimation, a critical task in motion analysis with applications in autonomous navigation, action recognition, and film production. Traditional optical flow methods require consecutive frames, which are often unavailable due to limitations in data acquisition or real-world scene disruptions. Thus, single-frame optical flow estimation is emerging in the literature. However, existing single-frame approaches suffer from two major limitations: (1) they rely on labeled training data, making them task-specific, and (2) they produce deterministic predictions, failing to capture motion uncertainty. To overcome these challenges, we propose ProbDiffFlow, a training-free framework that estimates optical flow distributions from a single image. Instead of directly predicting motion, ProbDiffFlow follows an estimation-by-synthesis paradigm: it first generates diverse plausible future frames using a diffusion-based model, then estimates motion from these synthesized samples using a pre-trained optical flow model, and finally aggregates the results into a probabilistic flow distribution. This design eliminates the need for task-specific training while capturing multiple plausible motions. Experiments on both synthetic and real-world datasets demonstrate that ProbDiffFlow achieves superior accuracy, diversity, and efficiency, outperforming existing single-image and two-frame baselines.