Self-NeRF: A Self-Training Pipeline for Few-Shot Neural Radiance Fields

by   Jiayang Bai, et al.

Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued by its necessity for numerous calibrated views and its accuracy diminishes significantly in a few-shot setting. To address this challenge, we propose Self-NeRF, a self-evolved NeRF that iteratively refines the radiance fields with very few number of input views, without incorporating additional priors. Basically, we train our model under the supervision of reference and unseen views simultaneously in an iterative procedure. In each iteration, we label unseen views with the predicted colors or warped pixels generated by the model from the preceding iteration. However, these expanded pseudo-views are afflicted by imprecision in color and warping artifacts, which degrades the performance of NeRF. To alleviate this issue, we construct an uncertainty-aware NeRF with specialized embeddings. Some techniques such as cone entropy regularization are further utilized to leverage the pseudo-views in the most efficient manner. Through experiments under various settings, we verified that our Self-NeRF is robust to input with uncertainty and surpasses existing methods when trained on limited training data.


page 6

page 8


PANeRF: Pseudo-view Augmentation for Improved Neural Radiance Fields Based on Few-shot Inputs

The method of neural radiance fields (NeRF) has been developed in recent...

DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models

Under good conditions, Neural Radiance Fields (NeRFs) have shown impress...

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

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

Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes

Despite the success of deep learning methods for semantic segmentation, ...

MapNeRF: Incorporating Map Priors into Neural Radiance Fields for Driving View Simulation

Simulating camera sensors is a crucial task in autonomous driving. Altho...

Enhancement of Novel View Synthesis Using Omnidirectional Image Completion

We present a method for synthesizing novel views from a single 360-degre...

Please sign up or login with your details

Forgot password? Click here to reset