RegNeRF

Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs

Michael Niemeyer^1,2,3 Jonathan T. Barron³ Ben Mildenhall³

Mehdi S. M. Sajjadi³ Andreas Geiger^1,2 Noha Radwan³

¹Max Planck Institute for Intelligent Systems ²University of Tübingen ³Google Research

CVPR 2022 (oral)

More Results from our Method

View Synthesis with 3 Input Views

View Synthesis with 6 Input Views

View Synthesis with 9 Input Views

← Return to main page.

Citation

If you want to cite our work, please use:

        @InProceedings{Niemeyer2021Regnerf,
          author    = {Michael Niemeyer and Jonathan T. Barron and Ben Mildenhall and Mehdi S. M. Sajjadi and Andreas Geiger and Noha Radwan},  
          title     = {RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs},
          booktitle = {Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
          year      = {2022},
        }