Key Capabilities
Our novel, permutation-equivariant neural network reconstructs visual geometry without a fixed reference view, achieving robust, state-of-the-art performance.
Permutation-Equivariant
SOTA Performance
Robust & Efficient
Scalable Permutation-Equivariant Visual Geometry Learning
Our novel, permutation-equivariant neural network reconstructs visual geometry without a fixed reference view, achieving robust, state-of-the-art performance.
We visualize some in-the-wild videos, demonstrating the generalizability of our method.
💡 Please Note: To ensure a smooth interactive experience, the point clouds in this demo are downsampled. The quality of the full model is much higher.
Rotate
Hold & Drag Left Mouse
Pan
Hold & Drag Right Mouse
Zoom
Use Mouse Scroll Wheel