🤖 AI Summary
To address severe seam artifacts caused by global alignment failure in large-disparity image stitching, this paper proposes embedding a Local Patch Alignment Module (LPAM) into the seam cutting pipeline, enabling an integrated “cut-while-align” paradigm. Specifically, image patches are extracted from low-quality seam regions; dense correspondences are established via SIFT flow; and pixel-level realignment is achieved through local affine or homography optimization, followed by multi-frequency seamless blending. This work is the first to tightly couple local alignment with seam cutting, breaking the conventional two-stage “align-then-cut” framework. Evaluated on large-disparity datasets, our method achieves a 2.1 dB PSNR gain and a 0.045 SSIM improvement over baselines, while increasing inference time by less than 8%, thus striking a favorable balance between accuracy and efficiency.
📝 Abstract
Seam cutting methods have been proven effective in the composition step of image stitching, especially for images with parallax. However, current seam cutting can be seen as the subsequent step after the image alignment is settled. Its effectiveness usually depends on the fact that images can be roughly aligned such that a local region exists where an unnoticeable seam can be found. Current alignment methods often fall short of expectations for images with large parallax, and most efforts are devoted to improving the alignment accuracy. In this paper, we argue that by adding a simple Local Patch Alignment Module (LPAM) into the seam cutting, the final result can be efficiently improved for large parallax image stitching. Concretely, we first evaluate the quality of pixels along the estimated seam of the seam cutting method. Then, for pixels with low qualities, we separate their enclosing patches in the aligned images and locally align them by constructing modified dense correspondences via SIFT flow. Finally, we composite the aligned patches via seam cutting and merge them into the original aligned result to generate the final mosaic. Experiments show that introducing LPAM can effectively and efficiently improve the stitching results.