Skip to content

README.md

Latest commit

 

History

History
15 lines (12 loc) · 770 Bytes

README.md

File metadata and controls

15 lines (12 loc) · 770 Bytes

VIINTER

Implementation of VIINTER: View Interpolation With Implicit Neural Representations of Images

Quick Start Example

Dependencies: torch 1.12, clip, imageio, tqdm, skimage, argparse, PIL

Train a Stanford Light Field scene

  1. Download Chess scene here
  2. Move rectified to data/LF and rename as data/LF/Chess
  3. python train.py --data_dir data/LF --dset LF --scene Chess --clip 0.0

Train a LLFF scene

  1. Download flower scene here
  2. Move flower/images_4 under data/LLFF and rename as data/LLFF/flower
  3. python train.py --data_dir data/LLFF --dset LLFF --scene flower --clip 0.01