VM-NeRF: Tackling Sparsity in NeRF with View Morphing
This addresses a key limitation in NeRF for 3D scene reconstruction, particularly in sparse-view settings, though it is an incremental improvement over existing methods.
The paper tackles the problem of overfitting in Neural Radiance Fields (NeRF) when only a few input viewpoints are available, by introducing VM-NeRF, which uses view morphing to generate geometrically consistent image transitions during training, resulting in improved novel view synthesis with PSNR increases of up to 1.8dB for eight views and 1.0dB for four views.
NeRF aims to learn a continuous neural scene representation by using a finite set of input images taken from various viewpoints. A well-known limitation of NeRF methods is their reliance on data: the fewer the viewpoints, the higher the likelihood of overfitting. This paper addresses this issue by introducing a novel method to generate geometrically consistent image transitions between viewpoints using View Morphing. Our VM-NeRF approach requires no prior knowledge about the scene structure, as View Morphing is based on the fundamental principles of projective geometry. VM-NeRF tightly integrates this geometric view generation process during the training procedure of standard NeRF approaches. Notably, our method significantly improves novel view synthesis, particularly when only a few views are available. Experimental evaluation reveals consistent improvement over current methods that handle sparse viewpoints in NeRF models. We report an increase in PSNR of up to 1.8dB and 1.0dB when training uses eight and four views, respectively. Source code: \url{https://github.com/mbortolon97/VM-NeRF}