StableMotion: Repurposing Diffusion-Based Image Priors for Motion Estimation

TL;DR

StableMotion innovatively repurposes pretrained diffusion models for motion estimation tasks, achieving state-of-the-art results with significantly faster inference by introducing adaptive ensemble and sampling step strategies.

Contribution

The paper introduces StableMotion, a framework that transforms diffusion models into motion estimators and proposes novel strategies to improve efficiency and output quality.

Findings

Achieves state-of-the-art performance on image rectification tasks.

Provides 200x speedup over previous diffusion-based methods.

Demonstrates strong generalizability across tasks.

Abstract

We present StableMotion, a novel framework leverages knowledge (geometry and content priors) from pretrained large-scale image diffusion models to perform motion estimation, solving single-image-based image rectification tasks such as Stitched Image Rectangling (SIR) and Rolling Shutter Correction (RSC). Specifically, StableMotion framework takes text-to-image Stable Diffusion (SD) models as backbone and repurposes it into an image-to-motion estimator. To mitigate inconsistent output produced by diffusion models, we propose Adaptive Ensemble Strategy (AES) that consolidates multiple outputs into a cohesive, high-fidelity result. Additionally, we present the concept of Sampling Steps Disaster (SSD), the counterintuitive scenario where increasing the number of sampling steps can lead to poorer outcomes, which enables our framework to achieve one-step inference. StableMotion is verified on two image rectification tasks and delivers state-of-the-art performance in both, as well as showing strong generalizability. Supported by SSD, StableMotion offers a speedup of 200 times compared to previous diffusion model-based methods.