3d-mesh

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

This is a implementation of the 3D FLAME model in PyTorch

Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020

Tensorflow framework for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 2D or 3D keypoints, and how to generate textured head meshes from Images.

[NeurIPS 2024] MeshXL: Neural Coordinate Field for Generative 3D Foundation Models, a 3D fundamental model for mesh generation

State-of-the-art methods on monocular 3D pose estimation / 3D mesh recovery

TEMPEH reconstructs 3D heads in dense semantic correspondence from calibrated multi-view images in about 0.3 seconds.

This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.

Smplify-X implementation. (2025. 04. 07 No Error & Recent version)

Benchmark for visual localization on imperfect 3D mesh models from the Internet

Pythonic remeshing library based on the MMG software.

3D structured/unstructured/tetrahedral/hexahedral multi-block mesh generator with boolean operations based on gmsh

[Preprint] "Can 3D Adversarial Logos Cloak Humans?"

A real-time 3D function visualizer with a plug-and-play GPU pipeline—write simple compute shaders to create custom effects without dealing with complex rendering internals.

A collection of sensor maps collected by Google's Tango Tablet, accompanied with layout maps

Python generation pipeline behind a public MIT dataset of 2,023 unique glTF 2.0 Binary meshes (33.5 GB) for robot/cobot simulation, manipulation research and VLA training. Published on Hugging Face with dataset and pipeline DOIs.

Python module to query an fetch the 3D-ARD project

A 3d cloud mesh is generated from a, set of photos taken from a drone, in airsim environment.

Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping.

MeshRunner - Improved classification of 3D mesh objects