# zju3dv/NeuralRecon

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

Repository: https://github.com/zju3dv/NeuralRecon
Canonical: https://ross.abutalabs.com/products/neuralrecon
Homepage: https://zju3dv.github.io/neuralrecon/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: 3d-reconstruction, 3d-vision
Last push: 2023-10-04T11:35:56+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2010, "days_push": 1064, "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 2274, forks 312 (observed 2026-08-28T04:06:33.281225+00:00)

## What it is
NeuralRecon is a deep learning framework for real-time 3D scene reconstruction from monocular video with known camera poses. It reconstructs dense, coherent 3D geometry by sequentially predicting sparse TSDF volumes for video fragments using a neural network with a learning-based fusion module.

## Use cases
- reconstruct 3d scene geometry from monocular video in real time
- generate dense 3d surface models from iphone arkit captures
- run 3d reconstruction on scannet dataset with pretrained weights
- build coherent 3d meshes from video fragments using neural tsdf fusion
- evaluate 3d reconstruction accuracy on indoor scene datasets

## When to choose
- you need real-time dense 3d reconstruction from a single camera with known poses
- you want coherent geometry across frames rather than per-frame depth maps
- you have arkit or similar camera pose data from a mobile device
- you need a pretrained model that generalizes to new indoor scenes

## When to avoid
- you lack camera pose information for your video input
- you need textured or colored 3d reconstruction rather than geometry only
- you work outside linux or cannot set up the torchsparse dependency
- you need reconstruction of large outdoor scenes rather than indoor environments

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning, graphics, simulation
- domain: computer-vision, machine-learning, deep-learning, graphics, artificial-intelligence
- platform: python
- tags: 3d-reconstruction, monocular-video, tsdf, real-time, cvpr-2021, scannet, arkit, neural-networks, 3d-vision, surface-reconstruction, linux, gpu

## Member repositories
- zju3dv/NeuralRecon (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:33.281225+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 2026-08-30T02:41:38.843186+00:00, confidence not recorded.
  - readme: https://github.com/zju3dv/NeuralRecon (fetched 2026-08-28T04:06:33.281225+00:00, sha 19dd97e6f7c8)
  - homepage: https://zju3dv.github.io/neuralrecon/ (fetched 2026-08-29T10:22:03.110976+00:00, sha 12076345eabf)
- Data as of 2026-08-30T08:39:29.467469+00:00.