RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs

TL;DR

RegNeRF introduces regularization techniques for Neural Radiance Fields to improve view synthesis quality from sparse inputs by addressing geometry errors and training divergence, outperforming existing methods.

Contribution

The paper proposes novel regularization strategies for NeRF that enhance performance with limited input views, including geometry and appearance regularization and training annealing.

Findings

Outperforms other scene-specific NeRF models with sparse inputs

Reduces artifacts caused by geometry estimation errors

Achieves competitive results compared to pre-trained models

Abstract

Neural Radiance Fields (NeRF) have emerged as a powerful representation for the task of novel view synthesis due to their simplicity and state-of-the-art performance. Though NeRF can produce photorealistic renderings of unseen viewpoints when many input views are available, its performance drops significantly when this number is reduced. We observe that the majority of artifacts in sparse input scenarios are caused by errors in the estimated scene geometry, and by divergent behavior at the start of training. We address this by regularizing the geometry and appearance of patches rendered from unobserved viewpoints, and annealing the ray sampling space during training. We additionally use a normalizing flow model to regularize the color of unobserved viewpoints. Our model outperforms not only other methods that optimize over a single scene, but in many cases also conditional models that are extensively pre-trained on large multi-view datasets.