# facebookresearch/pifuhd

High-Resolution 3D Human Digitization from A Single Image.

Repository: https://github.com/facebookresearch/pifuhd
Canonical: https://ross.abutalabs.com/products/pifuhd
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-08-19T14:38:14+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2555, "days_push": 744, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9737, forks 1470 (observed 2026-08-28T04:10:37.016007+00:00)

## What it is
PIFuHD is a PyTorch implementation of a CVPR 2020 research model that reconstructs high-resolution 3D human body meshes from a single 2D image using multi-level pixel-aligned implicit functions. It provides test and visualization code plus pretrained model checkpoints.

## Use cases
- reconstruct a 3D human model from a single photo
- generate 3D mesh files of people from images
- create 3D avatars from portrait photos
- run high-resolution 3D human digitization research
- convert 2D images of people into obj files

## When to choose
- you need single-image 3D human reconstruction with high detail
- you have a GPU with at least 8GB memory and want pretrained inference
- you are reproducing or building on CVPR 2020 3D digitization research

## When to avoid
- you need full-body reconstruction of non-human objects or scenes
- you lack a CUDA GPU (CPU inference is impractical)
- you need actively maintained production software or training code
- you need real-time 3D reconstruction

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, deep-learning, graphics, machine-learning
- platform: python, cross-platform
- tags: 3d-reconstruction, human-digitization, implicit-function, pytorch, cvpr-2020, single-image, mesh-generation, research-code, gpu, linux

## Member repositories
- facebookresearch/pifuhd (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:37.016007+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 2026-08-29T17:21:12.891217+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/pifuhd (fetched 2026-08-28T04:10:37.016007+00:00, sha c0d6c516f6c7)
- Data as of 2026-08-30T08:39:29.467469+00:00.