SPIn-NeRF

The SPIn-NeRF dataset contains 10 scenes, each with 60 training views (with the object to be removed), 40 test views (without the object), and human-annotated object masks per view.

Data and Resources

Cite this as

Tristan Aumentado-Armstrong, Marcus A. Brubaker, Ashkan Mirzaei, Jonathan Kelly, Igor Gilitschenski, Konstantinos G. Derpanis, Alex Levinshtein (2024). Dataset: SPIn-NeRF. https://doi.org/10.57702/v9m9zxe0

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Tristan Aumentado-Armstrong
More Authors
Marcus A. Brubaker
Ashkan Mirzaei
Jonathan Kelly
Igor Gilitschenski
Konstantinos G. Derpanis
Alex Levinshtein
Homepage https://arxiv.org/abs/2303.12345