Instant uncertainty calibration of NERFs using a meta-calibrator
Neural Radiance Fields (NeRFs) have markedly improved novel view synthesis, but accurate uncertainty quantification in their image predictions remains an open problem. The prevailing methods for estimating uncertainty, including the state-of-the-art Density-aware NeRF Ensembles (DANE) [29], quantify...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2024
|