# kakaobrain/nerf-factory

An awesome PyTorch NeRF library

Repository: https://github.com/kakaobrain/nerf-factory
Canonical: https://ross.abutalabs.com/products/nerf-factory
Homepage: https://kakaobrain.github.io/NeRF-Factory
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-07-23T07:09:27+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1443, "days_push": 771, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1272, forks 103 (observed 2026-08-28T04:04:12.122873+00:00)

## What it is
A PyTorch library collecting reimplementations of seven popular NeRF (Neural Radiance Fields) models such as NeRF, Mip-NeRF, DVGO, and Ref-NeRF, along with seven standard NeRF benchmark datasets. It provides a unified, extensible framework for training and evaluating NeRF models via Gin-configured run commands.

## Use cases
- reproduce NeRF research baselines in PyTorch
- train neural radiance field models on standard datasets
- compare NeRF, Mip-NeRF, DVGO, and Plenoxels implementations
- benchmark novel view synthesis models
- extend NeRF models for new research experiments
- download and prepare standard NeRF benchmark datasets

## When to choose
- you need consistent PyTorch reimplementations of multiple classic NeRF models for research comparison
- you want a single framework with bundled dataset handling for NeRF benchmarks
- you are studying NeRF variants and want reference implementations with checkpoints

## When to avoid
- you need actively maintained code - the repository is deprecated and development moved to POSTECH-CVLab/NeRF-Factory
- you need modern 3D reconstruction methods like 3D Gaussian Splatting
- you want a production-ready 3D capture pipeline rather than a research codebase

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, graphics, simulation
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python
- tags: nerf, neural-radiance-fields, pytorch, 3d-reconstruction, novel-view-synthesis, deprecated, research, gpu, linux

## Member repositories
- kakaobrain/nerf-factory (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:12.122873+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:03:17.891433+00:00, confidence not recorded.
  - readme: https://github.com/kakaobrain/nerf-factory (fetched 2026-08-28T04:04:12.122873+00:00, sha 6d92d4634536)
- Data as of 2026-08-30T08:39:29.467469+00:00.