luqspy/ResFCN256-3D-Reconstruction

ResFCN256-3D-Reconstruction implements a custom deep learning pipeline for dense 3D facial geometry estimation. At its core is a ResFCN256 (Residual Fully Convolutional Network) trained for 100 epochs on a dataset of 63,000 augmented images to perform direct regression of 3D facial coordinates from single 2D inputs

15
/ 100
Experimental
No Package No Dependents
Maintenance 6 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

MIT

Category

monocular-depth-estimation

Last pushed

Dec 07, 2025

Commits (30d)

0

GitHub
Monocular Depth Estimation · 31 frameworks

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/luqspy/ResFCN256-3D-Reconstruction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

ialhashim/DenseDepth

High Quality Monocular Depth Estimation via Transfer Learning

51

cake-lab/HybridDepth

Official implementation for HybridDepth Model [WACV 2025, ISMAR 2024]

51

tinghuiz/SfMLearner

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

51

soubhiksanyal/RingNet

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

51

nianticlabs/monodepth2

[ICCV 2019] Monocular depth estimation from a single image

51

Explore ML Frameworks

All categories Trending ML Framework directory Insights