FrameNeRF: A Simple and Efficient Framework for Few-shot Novel View Synthesis
This work addresses the challenge of training stable, high-quality neural radiance fields with limited input views, which is important for applications like virtual reality and 3D reconstruction, but it is incremental as it builds on existing NeRF models.
The paper tackles the problem of few-shot novel view synthesis by proposing FrameNeRF, a framework that uses a regularization model to generate dense views from sparse inputs, enabling the training of fast high-fidelity NeRF models, achieving state-of-the-art performance on benchmark datasets.
We present a novel framework, called FrameNeRF, designed to apply off-the-shelf fast high-fidelity NeRF models with fast training speed and high rendering quality for few-shot novel view synthesis tasks. The training stability of fast high-fidelity models is typically constrained to dense views, making them unsuitable for few-shot novel view synthesis tasks. To address this limitation, we utilize a regularization model as a data generator to produce dense views from sparse inputs, facilitating subsequent training of fast high-fidelity models. Since these dense views are pseudo ground truth generated by the regularization model, original sparse images are then used to fine-tune the fast high-fidelity model. This process helps the model learn realistic details and correct artifacts introduced in earlier stages. By leveraging an off-the-shelf regularization model and a fast high-fidelity model, our approach achieves state-of-the-art performance across various benchmark datasets.