Reproduce “Generative Panoramic Image Stitching” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mathieu Tuli, Kaveh Kamali, David B. Lindell
The authors present a generative method for stitching casual photos into panoramas. It uses feature matching and homographies for a coarse layout, then fine-tunes an inpainting diffusion model with positional information to outpaint from a reference view. On casually captured scenes, DreamSim is 0.137 versus RealFill’s 0.197; AutoStitch performs better on feature-matching measures, and comparisons use tripod-derived panoramas, not ground truth.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.