DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis

TL;DR

DMAligner introduces a diffusion model-based view synthesis framework for image alignment, effectively addressing occlusion and illumination challenges that hinder traditional optical flow methods, and demonstrates superior performance on new and existing datasets.

Contribution

The paper proposes a novel diffusion-based image alignment method with a dynamics-aware training approach and a new dataset, improving robustness and accuracy over classical flow-based techniques.

Findings

Outperforms traditional optical flow methods on DSIA benchmark

Effectively handles occlusions and illumination variations

Demonstrates superior qualitative results on video datasets

Abstract

Image alignment is a fundamental task in computer vision with broad applications. Existing methods predominantly employ optical flow-based image warping. However, this technique is susceptible to common challenges such as occlusions and illumination variations, leading to degraded alignment visual quality and compromised accuracy in downstream tasks. In this paper, we present DMAligner, a diffusion-based framework for image alignment through alignment-oriented view synthesis. DMAligner is crafted to tackle the challenges in image alignment from a new perspective, employing a generation-based solution that showcases strong capabilities and avoids the problems associated with flow-based image warping. Specifically, we propose a Dynamics-aware Diffusion Training approach for learning conditional image generation, synthesizing a novel view for image alignment. This incorporates a Dynamics-aware Mask Producing (DMP) module to adaptively distinguish dynamic foreground regions from static backgrounds, enabling the diffusion model to more effectively handle challenges that classical methods struggle to solve. Furthermore, we develop the Dynamic Scene Image Alignment (DSIA) dataset using Blender, which includes 1,033 indoor and outdoor scenes with over 30K image pairs tailored for image alignment. Extensive experimental results demonstrate the superiority of the proposed approach on DSIA benchmarks, as well as on a series of widely-used video datasets for qualitative comparisons. Our code is available at https://github.com/boomluo02/DMAligner.