# sunset1995/DirectVoxGO

Direct voxel grid optimization for fast radiance field reconstruction.

Repository: https://github.com/sunset1995/DirectVoxGO
Canonical: https://ross.abutalabs.com/products/directvoxgo
Homepage: https://sunset1995.github.io/dvgo
Language: Python
License: NOASSERTION
License Family: other
Topics: directvoxgo, dvgo, nerf, neural-radiance-fields, cvpr2022
Last push: 2023-05-15T23:01:32+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1785, "days_push": 1206, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1075, forks 107 (observed 2026-08-28T04:03:29.172564+00:00)

## What it is
DirectVoxGO (DVGO) is a PyTorch implementation of Direct Voxel Grid Optimization for fast neural radiance field (NeRF) reconstruction, replacing NeRF's MLP with dense voxel grids for super-fast training convergence. It supports bounded, unbounded, and forward-facing scene datasets and includes a JIT-compiled CUDA extension for additional speedup.

## Use cases
- reconstruct a 3D radiance field from posed images quickly
- speed up NeRF training by replacing the MLP with a voxel grid
- render fly-through videos from casually captured forward-facing scenes
- train novel view synthesis models on NeRF, NSVF, BlendedMVS, or mip-NeRF360 datasets
- evaluate novel view synthesis with SSIM and LPIPS metrics

## When to choose
- you need fast NeRF-style training convergence (minutes rather than hours)
- you want a research baseline for voxel-based radiance field methods
- you have a CUDA GPU and posed multi-view images

## When to avoid
- you need real-time rendering on low-end hardware without GPUs
- you want the latest radiance field methods like 3D Gaussian splatting
- you need a maintained production library - the repo is research code from CVPR 2022

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, graphics, image-processing
- domain: computer-vision, graphics, deep-learning, machine-learning
- platform: python
- tags: nerf, radiance-fields, voxel-grid, novel-view-synthesis, cvpr2022, pytorch, 3d-reconstruction, linux, gpu, cuda

## Member repositories
- sunset1995/DirectVoxGO (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:29.172564+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 2026-08-30T06:53:28.410228+00:00, confidence not recorded.
  - readme: https://github.com/sunset1995/DirectVoxGO (fetched 2026-08-28T04:03:29.172564+00:00, sha d44e20975804)
  - homepage: https://sunset1995.github.io/dvgo (fetched 2026-08-29T12:55:25.868631+00:00, sha 3148de9729b4)
- Data as of 2026-08-30T08:39:29.467469+00:00.