🛠️ 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. Click 🚀 Start Reconstruction to launch the pipeline.
4. 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.

🌀 Rendering & 3D Model

• Render the scene from a circular path of novel views.
• Or from camera views close to the original input.

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.

Preloaded models coming soon. (TODO)