Learning Generalizable Light Field Networks from Few Images
This addresses the problem of efficient novel view synthesis for computer vision applications, but it is incremental as it builds on existing neural radiance field approaches.
The paper tackles few-shot novel view synthesis by using a neural light field representation that maps rays to colors directly, achieving competitive performance with state-of-the-art methods while offering 100 times faster rendering.
We explore a new strategy for few-shot novel view synthesis based on a neural light field representation. Given a target camera pose, an implicit neural network maps each ray to its target pixel's color directly. The network is conditioned on local ray features generated by coarse volumetric rendering from an explicit 3D feature volume. This volume is built from the input images using a 3D ConvNet. Our method achieves competitive performances on synthetic and real MVS data with respect to state-of-the-art neural radiance field based competition, while offering a 100 times faster rendering.