🛠️ How to Use This Demo

1. Upload a front-facing video or a folder of images of a static scene.
2. Use the sliders to configure the number of reference views, correspondences, and optimization steps.
3. First press on preprocess Input to extract frames from video(for videos) and COLMAP frames.
4. Then click 🚀 Start Reconstruction to actually launch the reconstruction pipeline.
5. Watch the training visualization and explore the 3D model. ‼️ If you see nothing in the 3D model viewer, try rotating or zooming — sometimes the initial camera orientation is off.

✅ Best for scenes with small camera motion. ❗ For full 360° or large-scale scenes, we recommend the Colab version (see project page).

📖 Detailed Overview

If you uploaded a video, it will be automatically cut into a smaller number of frames (default: 16).

The model pipeline:

1. 🧠 Runs PyCOLMAP to estimate camera intrinsics & poses (~3–7 seconds for <16 images).
2. 🔁 Computes 2D-2D correspondences between views. More correspondences generally improve quality.
3. 🔧 Optimizes a 3D Gaussian Splatting model for several steps.

🎥 Training Visualization

You will see a visualization of the entire training process in the "Training Video" pane.

🌀 3D Model

The 3D model is shown in the right viewer. You can explore it interactively:

• On PC: WASD keys, arrow keys, and mouse clicks
• On mobile: pan and pinch to zoom

🕒 Note: the 3D viewer takes a few extra seconds (~5s) to display after training ends.