Surflo: Consistent 3D Surface Flow Model with Global State
Researchers have introduced Surflo, a novel 3D surface reconstruction model that processes unposed RGB views into a global latent state. This approach allows for the decoding of oriented 3D surface points through flow matching, enabling arbitrary output resolutions from a few thousand to over a million points in a single pass. Surflo demonstrates competitive performance against existing feed-forward methods while being significantly faster than optimization-based techniques, offering a unique combination of global latent representation and flexible decoding. AI
IMPACT Enables flexible and efficient 3D surface reconstruction from multiple views, potentially impacting fields like computer graphics and robotics.