Data

Tools

Indexes

Applications

Experiments

Open Source Science

hashnerf-accelerating-nerf-training-with-multiresolution-hash-encoding

https://github.com/ninghsia/hashnerf-accelerating-nerf-training-with-multiresolution-hash-encoding

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: NingHsia
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 1.16 GB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License Citation

README.md

HashNeRF Accelerating NeRF Training with Multiresolution Hash Encoding

This is the final project for COMS W4732 Computer Vision II. Report is available here.

This project is built on top of HashNeRF-pytorch implementation.

Getting Started

Requirements

Install all required packages: pip install -r requirements.txt

Data

Download data from here: Google Drive. Unzip it, and put the 'data' folder into the repo folder.

Training HashNeRF

HashNeRF

To train a fern HashNeRF model: python run_nerf.py --config configs/fern.txt To train for other objects, replace configs/fern.txt with configs/{object}.txt. You can choose from fern, room, orchids, and leaves.

(Noted that if you place the 'data' folder in a different location from the provided instructions, you will need to update the datadir in the config file accordingly.

You'll see the rendering results in folder logs.

Variation of HashneRF

To train a fern HashNeRF-3RGB model mentioned in the report experiment section: python run_nerf.py --config configs/fern.txt --variation 3RGB To train a fern HashNeRF-DRGB model mentioned in the report experiment section: python run_nerf.py --config configs/fern.txt --variation DRGB

Owner

  • Login: NingHsia
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: HashNeRF-pytorch
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Yash
    family-names: Bhalgat
    email: yashbhalgat95@gmail.com
    affiliation: University of Oxford
    orcid: 'https://orcid.org/0000-0001-7775-6250'
url: 'https://github.com/yashbhalgat/HashNeRF-pytorch'
abstract: >-
  HashNeRF-pytorch is a pure PyTorch Implementation of the
  NVIDIA paper on Instant Training of Neural Graphics
  primitives (Instant-NGP). This codebase was built with the
  purpose of enabling AI Researchers to play around and
  innovate further upon this method.
keywords:
  - machine learning
  - artificial intelligence
  - computer vision
  - computer graphics
  - nerf
  - 3D reconstruction
  - neural rendering
license: MIT
version: '1.0'
date-released: '2022-06-01'

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • configargparse *
  • imageio >=2.34.0
  • imgviz >=1.2.2
  • kornia >=0.7.1
  • numpy >=1.24.4
  • opencv-python-headless >=4.9.0.80
  • pyvista >=0.43.3
  • scikit-image >=0.17.2
  • scikit-learn >=0.23.2
  • torch ==2.2.1
  • tqdm *