# nerfstudio-project/nerfacc

A General NeRF Acceleration Toolbox in PyTorch.

Repository: https://github.com/nerfstudio-project/nerfacc
Canonical: https://ross.abutalabs.com/products/nerfacc
Homepage: https://www.nerfacc.com/
Language: Python
License: NOASSERTION
License Family: other
Topics: instant-ngp, nerf, pytorch, rendering
Last push: 2024-10-02T17:54:16+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1455, "days_push": 700, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1456, forks 120 (observed 2026-08-28T04:04:46.906711+00:00)

## What it is
NerfAcc is a PyTorch acceleration toolbox for Neural Radiance Fields (NeRF), focused on efficient sampling in the volumetric rendering pipeline. It is plug-and-play with most NeRF codebases, providing significant training and inference speedups with minimal code changes.

## Use cases
- accelerate NeRF training in PyTorch
- speed up volumetric rendering of radiance fields
- add efficient ray sampling to an existing NeRF implementation
- train Instant-NGP-style models faster
- optimize NeRF inference performance
- plug-and-play acceleration for NeRF research codebases

## When to choose
- you are training or deploying NeRF/radiance field models in PyTorch and need faster sampling
- you want drop-in speedups for existing NeRF codebases with minimal modifications
- you need a pure Python API with flexible volumetric rendering primitives

## When to avoid
- your project does not use PyTorch or CUDA-capable GPUs
- you are working on general 3D rendering unrelated to radiance fields
- you need actively developed features - the project appears to be in maintenance mode

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, graphics, simulation, gpu-computing
- domain: computer-vision, graphics, machine-learning, deep-learning
- platform: python, windows
- tags: nerf, radiance-fields, volumetric-rendering, pytorch, cuda, instant-ngp, 3d-reconstruction, neural-rendering, linux, gpu

## Member repositories
- nerfstudio-project/nerfacc (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.906711+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 2026-08-30T04:35:37.145305+00:00, confidence not recorded.
  - readme: https://github.com/nerfstudio-project/nerfacc (fetched 2026-08-28T04:04:46.906711+00:00, sha 52f5819c6ffe)
- Data as of 2026-08-30T08:39:29.467469+00:00.