INCREMENTAL TENSOR DECOMPOSITION FOR FEW SHOT NEURAL RADIANCE FIELD

Neural Radiance Field (NeRF) stands out by demonstrating photo-realistic renderings, while it suffers from quality degradation when given only a few shot inputs. This paper aims to improve the rendering quality of NeRF from a few shot inputs. Original NeRF tends to overfit input views rapidly at the initial training stage when trained on sparse inputs. We address this challenge by presenting a novel incremental tensor decomposition method, where the resolution of decomposed tensors increases with the training iteration, enabling coarse to fine learning and alleviating the overfitting during the early stage. We offer several regularizations based on the proposed incremental learning process, including patch-based density regularization and depth regularization. Our proposed method outperforms previous baselines on the Realistic Synthetic 360 degrees dataset and achieves state-of-the-art results in PSNR.