Learning Generalizable Light Field Networks from Few Images

by   Qian Li, et al.

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.


page 1

page 11

page 13

page 20

page 21


Learning Neural Light Fields with Ray-Space Embedding Networks

Neural radiance fields (NeRFs) produce state-of-the-art view synthesis r...

InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering

We present an information-theoretic regularization technique for few-sho...

Single-image Tomography: 3D Volumes from 2D X-Rays

As many different 3D volumes could produce the same 2D x-ray image, inve...

R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis

Recent research explosion on Neural Radiance Field (NeRF) shows the enco...

Light Field Segmentation From Super-pixel Graph Representation

Efficient and accurate segmentation of light field is an important task ...

V4D: Voxel for 4D Novel View Synthesis

Neural radiance fields have made a remarkable breakthrough in the novel ...

Please sign up or login with your details

Forgot password? Click here to reset