# nianticlabs/simplerecon

[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions

Repository: https://github.com/nianticlabs/simplerecon
Canonical: https://ross.abutalabs.com/products/simplerecon
Language: Python
License: NOASSERTION
License Family: other
Topics: computer-vision, cost-volume, depth, depth-estimation, eccv2022, multi-view-stereo, mvs, pytorch, scannet, visualization
Last push: 2025-05-09T13:05:38+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 20, release rhythm 35, longevity 100
- inputs: {"age_days": 1513, "days_push": 481, "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 1428, forks 130 (observed 2026-08-28T04:04:42.041806+00:00)

## What it is
SimpleRecon is the reference PyTorch implementation of an ECCV 2022 paper for multi-view stereo depth estimation and 3D reconstruction that avoids 3D convolutions. It provides training, evaluation, point cloud fusion, mesh metrics, and visualization tooling for MVS depth models, primarily benchmarked on ScanNetv2.

## Use cases
- estimate depth maps from multiple posed images
- reconstruct 3D point clouds or meshes from video frames
- evaluate multi-view stereo models on ScanNet
- train or finetune an MVS depth estimation network
- visualize cost volumes and depth predictions
- run 3D scene reconstruction without 3D convolutions

## When to choose
- you need state-of-the-art multi-view stereo depth estimation with a fast 2D-CNN architecture
- you want a research baseline or pretrained weights for MVS on ScanNetv2
- you need point cloud fusion and mesh evaluation tooling alongside depth prediction

## When to avoid
- you need a commercially licensed model - the code is non-commercial use only
- you want a production-ready 3D reconstruction pipeline rather than research code
- you lack posed multi-view images with camera intrinsics
- you need real-time reconstruction on CPU or mobile hardware

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing, data-visualization
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: multi-view-stereo, depth-estimation, cost-volume, 3d-reconstruction, pytorch, eccv2022, scannet, point-cloud-fusion, research-code, non-commercial-license, gpu, linux

## Member repositories
- nianticlabs/simplerecon (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:42.041806+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 2026-08-30T04:37:19.587936+00:00, confidence not recorded.
  - readme: https://github.com/nianticlabs/simplerecon (fetched 2026-08-28T04:04:42.041806+00:00, sha 5e4d3c6f68f2)
- Data as of 2026-08-30T08:39:29.467469+00:00.