Auto-regressive transformation for image alignment
It addresses image alignment for applications requiring robustness to extreme variations, though it appears incremental as it builds on iterative refinement and multi-scale representations.
The paper tackles the problem of image alignment in challenging conditions like feature-sparse regions and large deformations, resulting in a method that significantly outperforms state-of-the-art methods across diverse datasets.
Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges improves through iterative refinement of the transformation field while focusing on critical regions in multi-scale image representations. We thus propose Auto-Regressive Transformation (ART), a novel method that iteratively estimates the coarse-to-fine transformations within an auto-regressive framework. Leveraging hierarchical multi-scale features, our network refines the transformations using randomly sampled points at each scale. By incorporating guidance from the cross-attention layer, the model focuses on critical regions, ensuring accurate alignment even in challenging, feature-limited conditions. Extensive experiments across diverse datasets demonstrate that ART significantly outperforms state-of-the-art methods, establishing it as a powerful new method for precise image alignment with broad applicability.