SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions

by   Nagabhushan Somraj, et al.

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:


page 1

page 7

page 9

page 10

page 11

page 14

page 15


ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields

Neural radiance fields (NeRF) have achieved impressive performances in v...

Depth-supervised NeRF: Fewer Views and Faster Training for Free

One common failure mode of Neural Radiance Field (NeRF) models is fittin...

SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

Neural Radiance Field (NeRF) significantly degrades when only a limited ...

S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfaces

Neural rendering of implicit surfaces performs well in 3D vision applica...

CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations

Recent advances in neural radiance fields (NeRFs) achieve state-of-the-a...

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

Novel view synthesis with sparse inputs is a challenging problem for neu...

Neural Radiance Fields (NeRFs): A Review and Some Recent Developments

Neural Radiance Field (NeRF) is a framework that represents a 3D scene i...

Please sign up or login with your details

Forgot password? Click here to reset