Gaussian Splatting Pipeline
Last updated:
This is mostly for me to help me remember these steps, so it assumes you’re on a Mac. But it’s basically identical on other platforms, sans sips and with your own build of Rerun.
- Take a video
- TODO: details on this because that’s the most important part, but that’ll probably live on Patreon
- ffmpeg to extract images as frames
mkdir images && ffmpeg -i input.mov -vf "fps=2" ./images/out%04d.jpg- Change FPS depending on desired capture parallax
- (This part isn’t FOSS yet! But TODO: share my automation file) If using masks, use Image Processor to automate Photoshop Action
Shortcuts/Create Subject Mask- COLMAP wants mask files in .png format, so in Terminal
for i in *.jpg; do sips -s format png "$i" --out "${i%.jpg}.png"; done
- COLMAP wants mask files in .png format, so in Terminal
- COLMAP on image dir to generate point cloud
colmap gui- Automatic Reconstruction (white and red dot in toolbar)
- Set
WorkspaceandImagefolders - Set
Data typetoVideo FramesorImagesdepending- NOTE: Video Frames causes a crash for me @ FPS@2; investigate whether higher fps works correctly
- NOTE: From here we could perform a dense reconstruction of the sparse point cloud for photogrammetry purposes
- Set
- Brush to train gaussians on the point cloud
- Make sure the exported
sparse/,database.db, and theimages/directory are in the same folder, and open that folder in Brush ./brush_app
- Make sure the exported
- Rerun to visualize splat training as it’s happening (open before starting training)
./rerun-cli-0.33.1-aarch64-apple-darwin
- SuperSplat to clean up the file
- Get Sillay
