Drag with left click to rotate view

Scroll to zoom in/out

Drag with right click to move view

Moving forward and backward

Moving left and right

Moving upward and downward

Note: Results are downsampled 4 times for efficient online rendering. Also, we do not mask out any points for fair comparison.

Comparison

Attribute to our group-wise inference manner and prior geometry knowledge from pretrained video diffusion model, our model successfully produces consistent 4D geometry under fast motion (row 1) and deceptive reflection in the water (row 2).