Abstract: This paper introduces a novel self-supervised learning framework for enhancing 3D perception in autonomous driving scenes. Specifically, our approach, namely NCLR, focuses on 2D-3D neural ...
Abstract: The success of pre-trained 2D vision models can largely be attributed to their ability to learn from large-scale datasets. However, compared with 2D image datasets, current pre-training data ...
@misc{3dgsflats, title={3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction}, author={Maria Taktasheva, Lily Goli, Alessandro Fiorini, Zhen Li, Daniel Rebain, Andrea Tagliasacchi}, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback