# Hypernerf Practice

[Huggingface Link](https://huggingface.co/xieyizheng/hypernerf_practice)

This README contains overview on applyiing several custom scenes to reproduce the hypernerf project.
- hand
- dvd
- tomato-mark


## hand

most successful one, trained extensively on V100

interpolation:
![Image 1](gif/hand-interpolate.gif)
novelview:
![Image 2](gif/hand-novelview.gif)

PSNR: <br>
coarse metrics:  metric/psnr≈31.7468 <br>
fine metrics:  metric/psnr≈32.5462

## dvd

not so great

interpolation & novelview:
![Image 3](gif/dvd-interpolate-novelview.gif)

PSNR: <br>
coarse metrics:  metric/psnr≈  <br>
fine metrics:  metric/psnr≈ 

## tomato-mark

more artifacts

interpolation:
![Image 4](gif/tomato-mark-interpolate.gif)
PSNR: <br>
coarse metrics:  metric/psnr≈  <br>
fine metrics:  metric/psnr≈ 

# reproduction steps

Due to deprecation, the hypernerf project doesn't work out of the box. <br>
We need code modifications to the environments, dependencies set up and rendering part. <br>
For this reproduction, I only used the notebooks. <br>
The provided instructions below are guaranteed to work. <br>
[Click to reproduction steps](reproduction-instruction.md)

# Dataset:







---
language: 
  - en

thumbnail:

tags:

license: 

datasets:

metrics:

---