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.

翻译：近来，神经辐射场（NeRF）作为一种从密集图像集中合成新视角的有效方法而兴起。尽管其性能令人印象深刻，但NeRF因需要大量已标定视角而受到困扰，并且在少样本设置下其准确性显著下降。为应对这一挑战，我们提出了Self-NeRF，一种自进化型NeRF，它能够在输入视角极少的情况下迭代优化辐射场，而无需引入额外先验。基本上，我们通过同时在参考视图和未见视图的监督下迭代训练模型。在每次迭代中，我们使用前一次迭代生成的模型预测颜色或翘曲像素来标注未见视图。然而，这些扩展的伪视图存在颜色不准确和翘曲伪影的问题，从而降低了NeRF的性能。为缓解此问题，我们构建了一个具有专用嵌入的不确定性感知NeRF。进一步利用锥体熵正则化等技术，以最有效的方式利用伪视图。通过在不同设置下的实验，我们验证了Self-NeRF对输入中的不确定性具有鲁棒性，并且在有限训练数据下训练时优于现有方法。