# YuliangXiu/ECON

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

Repository: https://github.com/YuliangXiu/ECON
Canonical: https://ross.abutalabs.com/products/econ
Homepage: https://xiuyuliang.cn/econ
Language: Python
License: NOASSERTION
License Family: other
Topics: 3d-reconstruction, avatar-generator, computer-graphics, computer-vision, digital-twins, metaverse, normal-maps, pifu, pifuhd, smpl-body, smplx, virtual-humans
Last push: 2024-09-17T21:59:40+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": 1431, "days_push": 715, "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 1206, forks 116 (observed 2026-08-28T04:03:59.355229+00:00)

## What it is
ECON is a research tool that reconstructs high-fidelity 3D clothed human avatars from a single color image by combining implicit and explicit surface representations with SMPL-X guidance. It supports multi-person reconstruction, SMPL-X-based animation, and ships with demos on HuggingFace and Google Colab.

## Use cases
- reconstruct a 3D clothed human avatar from a single photo
- generate digital human models for the metaverse or digital twins
- handle 3D human reconstruction with loose clothing or challenging poses
- animate reconstructed humans using SMPL-X
- reconstruct multiple people from one image
- replace noisy face or hand geometry with clean SMPL-X parts

## When to choose
- you need high-fidelity 3D humans from single in-the-wild images, including loose clothing
- you want a research-grade CVPR 2023 method with pretrained models and demos
- you need SMPL-X-compatible output for downstream animation pipelines

## When to avoid
- you need real-time or production-grade avatar generation at scale
- you lack a GPU or cannot set up a heavy PyTorch research environment
- you need a simple off-the-shelf app rather than a research codebase with a non-standard license

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing, deep-learning
- domain: computer-vision, graphics, machine-learning, artificial-intelligence
- platform: python, windows
- tags: 3d-reconstruction, human-digitization, avatar-generation, smpl-x, normal-maps, implicit-surfaces, cvpr-2023, pytorch, gpu, docker, linux

## Member repositories
- YuliangXiu/ECON (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.355229+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 2026-08-30T06:19:16.263675+00:00, confidence not recorded.
  - readme: https://github.com/YuliangXiu/ECON (fetched 2026-08-28T04:03:59.355229+00:00, sha af081055cc12)
  - homepage: https://xiuyuliang.cn/econ (fetched 2026-08-29T12:26:57.988975+00:00, sha f49f22ab7d0e)
- Data as of 2026-08-30T08:39:29.467469+00:00.