# karfly/learnable-triangulation-pytorch

This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!

Repository: https://github.com/karfly/learnable-triangulation-pytorch
Canonical: https://ross.abutalabs.com/products/learnable-triangulation-pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2023-10-03T21:34:46+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2667, "days_push": 1065, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1135, forks 184 (observed 2026-08-28T04:03:43.569718+00:00)

## What it is
Official PyTorch implementation of the ICCV 2019 paper 'Learnable Triangulation of Human Pose', providing algebraic and volumetric learnable triangulation methods for multi-view 3D human pose estimation. It includes training and evaluation pipelines, pretrained models, and configs for the Human3.6M dataset.

## Use cases
- estimate 3d human pose from multiple camera views
- reproduce state-of-the-art multi-view pose estimation results
- train a 3d pose model on human3.6m
- evaluate pretrained 3d pose estimation models
- research learnable triangulation methods
- get 3d skeletons from calibrated multi-camera video

## When to choose
- you need multi-view 3D human pose estimation with pretrained models
- you want to reproduce or build on the ICCV 2019 learnable triangulation paper
- you work with the Human3.6M dataset in PyTorch

## When to avoid
- you need single-camera 3D pose estimation
- you need datasets other than Human3.6M, such as CMU Panoptic
- you need a production-ready, actively maintained pose estimation service

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: 3d-human-pose-estimation, multi-view, triangulation, pytorch, research-code, iccv-2019

## Member repositories
- karfly/learnable-triangulation-pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:43.569718+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 2026-08-30T06:36:47.734391+00:00, confidence not recorded.
  - readme: https://github.com/karfly/learnable-triangulation-pytorch (fetched 2026-08-28T04:03:43.569718+00:00, sha ec537b82c284)
- Data as of 2026-08-30T08:39:29.467469+00:00.