Michał Tyszkiewicz(@jatentaki):Feed-forward 3D reconstruction should not be limited to predicting one Gaussian per pixel. We introduce TokenGS, which uses learnable tokens to decouple the 3D Gaussian prediction from the image resolution and the number of input views. #CVPR2026Highlight [1/6]

Michał Tyszkiewicz

@jatentaki

Senior research scientist @ NVIDIA Spatial Intelligence Lab, PhD from EPFL

Joined June 2020

168 Following 447 Followers

Michał Tyszkiewicz@jatentaki

2026.04.17 16:44

Feed-forward 3D reconstruction should not be limited to predicting one Gaussian per pixel. We introduce TokenGS, which uses learnable tokens to decouple the 3D Gaussian prediction from the image resolution and the number of input views. #CVPR2026Highlight# [1/6]