Markus Steinberger

Unlock controllable video generation by disentangling appearance from semantics within self-supervised DINO features, enabling robust video domain transfer and video-from-3D generation.

Stop avatars from looking like they're having a seizure: this method uses autoregressive prediction of appearance latents to create temporally stable and high-fidelity 3D Gaussian avatars.

Unlock 4-15% faster Gaussian Splatting without retraining your existing datasets by swapping in a polynomial kernel.