The original Stonehenge video is here: https://www.youtube.com/watch?v=UrLUfDhHe-A
1) I use the yt-dlp package for downloading the youtube video (1440p)
2) used ffmpeg to extract frames at 1 fps, totaling 534 frames.
3) used colmap 3.13dev0+glomap to create poses for the images. It uses vocab_tree_matcher and detects 531 images. Finally I undistort it with colmap image_undistorter
4) I use Lichtfeld Studio with for 30k iters. Using 5 M splats (before sparsity) and 2 M splats (after sparsity).
5) imported the gaussian splat to supersplat, cleaned it, rotated it, and publish it with SOG