SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions

TL;DR

SimpleNeRF introduces a regularization approach that uses simpler, augmented models to supervise depth estimation in sparse-view neural radiance fields, improving view synthesis quality without relying on pre-trained models.

Contribution

The paper proposes a novel method to learn depth supervision through augmented models that promote simpler solutions, enhancing sparse-view NeRF training.

Findings

Achieves state-of-the-art view synthesis on two datasets.

Effectively supervises NeRF depth with simpler models.

Improves performance without pre-trained depth models.

Abstract

Neural Radiance Fields (NeRF) show impressive performance for the photorealistic free-view rendering of scenes. However, NeRFs require dense sampling of images in the given scene, and their performance degrades significantly when only a sparse set of views are available. Researchers have found that supervising the depth estimated by the NeRF helps train it effectively with fewer views. The depth supervision is obtained either using classical approaches or neural networks pre-trained on a large dataset. While the former may provide only sparse supervision, the latter may suffer from generalization issues. As opposed to the earlier approaches, we seek to learn the depth supervision by designing augmented models and training them along with the NeRF. We design augmented models that encourage simpler solutions by exploring the role of positional encoding and view-dependent radiance in training the few-shot NeRF. The depth estimated by these simpler models is used to supervise the NeRF depth estimates. Since the augmented models can be inaccurate in certain regions, we design a mechanism to choose only reliable depth estimates for supervision. Finally, we add a consistency loss between the coarse and fine multi-layer perceptrons of the NeRF to ensure better utilization of hierarchical sampling. We achieve state-of-the-art view-synthesis performance on two popular datasets by employing the above regularizations. The source code for our model can be found on our project page: https://nagabhushansn95.github.io/publications/2023/SimpleNeRF.html