# autonomousvision/occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

Repository: https://github.com/autonomousvision/occupancy_networks
Canonical: https://ross.abutalabs.com/products/occupancy_networks
Homepage: https://avg.is.tuebingen.mpg.de/publications/occupancy-networks
Language: Python
License: MIT
License Family: permissive
Last push: 2023-06-27T00:23:54+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": 2711, "days_push": 1164, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1663, forks 303 (observed 2026-08-28T04:05:18.798155+00:00)

## What it is
Official PyTorch implementation of the CVPR 2019 paper 'Occupancy Networks: Learning 3D Reconstruction in Function Space'. It learns continuous 3D occupancy functions to reconstruct 3D meshes from single images, including pretrained models and training/evaluation pipelines on ShapeNet.

## Use cases
- reconstruct 3D meshes from single images
- train occupancy network models on ShapeNet
- evaluate 3D reconstruction models
- generate meshes from demo input images
- research implicit 3D shape representations

## When to choose
- you need single-view 3D reconstruction with occupancy-based implicit representations
- you want to reproduce or build on the Occupancy Networks paper
- you need pretrained models and preprocessing pipelines for ShapeNet

## When to avoid
- you need real-time 3D reconstruction on low-end hardware without a CUDA GPU
- you want a production-ready 3D reconstruction service rather than research code
- you need recent state-of-the-art neural reconstruction methods

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, graphics
- platform: python
- tags: 3d-reconstruction, occupancy-networks, shapenet, mesh-generation, cvpr-2019, research-code, pytorch, linux, gpu

## Member repositories
- autonomousvision/occupancy_networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:18.798155+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 2026-08-30T03:44:31.448908+00:00, confidence not recorded.
  - readme: https://github.com/autonomousvision/occupancy_networks (fetched 2026-08-28T04:05:18.798155+00:00, sha 28f083b607bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.