Data Augmentation for NeRFs in the Low Data Limit
This work addresses the challenge of robust scene reconstruction for robotic tasks in resource-constrained, unknown environments, though it is incremental as it builds on existing NeRF methods.
The paper tackles the problem of Neural Radiance Fields failing in low-data scenarios with incomplete scene data by proposing a data augmentation method using rejection sampling from a posterior uncertainty distribution, resulting in 39.9% better performance and 87.5% less variability compared to state-of-the-art baselines.
Current methods based on Neural Radiance Fields fail in the low data limit, particularly when training on incomplete scene data. Prior works augment training data only in next-best-view applications, which lead to hallucinations and model collapse with sparse data. In contrast, we propose adding a set of views during training by rejection sampling from a posterior uncertainty distribution, generated by combining a volumetric uncertainty estimator with spatial coverage. We validate our results on partially observed scenes; on average, our method performs 39.9% better with 87.5% less variability across established scene reconstruction benchmarks, as compared to state of the art baselines. We further demonstrate that augmenting the training set by sampling from any distribution leads to better, more consistent scene reconstruction in sparse environments. This work is foundational for robotic tasks where augmenting a dataset with informative data is critical in resource-constrained, a priori unknown environments. Videos and source code are available at https://murpheylab.github.io/low-data-nerf/.