awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
facebookresearch avatar

facebookresearch/pifuhdArchived

0
View on GitHub↗
9,743 stars·1,476 forks·Python·20 views

Pifuhd

pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D image. It utilizes pixel-aligned implicit functions to map image pixels to 3D space, predicting surface occupancy and distance to create detailed geometry.

The system includes a pipeline for creating digital human assets, moving from 2D image feature projection to the extraction of discrete triangular meshes. It features specialized tools for refining these models, including a post-processor that removes geometric artifacts by isolating the largest connected component of the mesh.

The framework also provides visualization capabilities, such as a geometry visualizer that renders rotating turn-table animations to inspect reconstructed models from multiple angles.

Features

  • Human Reconstruction - Generates high-resolution 3D meshes of people from a single 2D image using pixel-aligned implicit functions.
  • Coordinate-Based Neural Representations - Uses neural networks that map spatial coordinates to scene properties to predict 3D geometry.
  • 2D-to-3D Feature Projections - Projects 2D image features into 3D space to guide the geometry reconstruction process.
  • Pixel-Aligned Implicit Functions - Utilizes pixel-aligned implicit functions to map image pixels to 3D space to create detailed geometry.
  • Image-to-Mesh Generation - Transforms 2D image inputs into 3D polygonal mesh representations using implicit surface predictions.
  • Volumetric Mesh Extraction - Converts continuous implicit surface representations into discrete 3D triangular meshes for rendering.
  • Single-Image 3D Reconstructions - Creates high-resolution 3D meshes of people from a single 2D image.
  • 3D Mesh Post-Processing - Cleans up reconstructed 3D models by removing noise and isolating the primary connected components of the mesh.
  • 3D Mesh Post-Processors - Includes a utility for cleaning reconstruction artifacts and isolating the main connected component of a 3D model.
  • Mesh Decomposition - Isolates the largest connected component of a mesh to remove floating geometry artifacts.
  • Mesh Artifact Removal - Provides a post-processor that removes geometric artifacts by isolating the largest connected component of the mesh.
  • 3D Reconstruction - Pixel-aligned implicit function for high-resolution human digitization.
  • Human Digitalization - Digitizes high-resolution 3D humans using multi-level implicit functions.

Star history

Star history chart for facebookresearch/pifuhdStar history chart for facebookresearch/pifuhd

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with Pifuhd

These projects share indexed features with Pifuhd. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • tencentarc/instantmeshTencentARC avatar

    TencentARC/InstantMesh

    4,431View on GitHub↗

    InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large reconstruction model to convert a single two-dimensional image into a three-dimensional object mesh. The system functions as a textured 3D mesh exporter, saving generated objects with either vertex colors or full texture maps for use in external rendering software. The framework covers a range of capabilities including feed-forward geometry inference, single-image depth estimation, and neural radiance fields. It also supports differentiable mesh rendering and workflows for spars

    Python
    View on GitHub↗4,431
  • ashawkey/stable-dreamfusionashawkey avatar

    ashawkey/stable-dreamfusion

    8,841View on GitHub↗

    This project is a diffusion-based 3D generator and image-to-3D reconstruction system. It translates natural language descriptions or two-dimensional images into three-dimensional assets using neural radiance fields and diffusion models. The system utilizes score-distillation sampling and diffusion-based guidance to refine 3D shapes without requiring 3D training data. It includes specialized tools for transforming neural representations into exportable meshes with texture and material data, as well as a pipeline for iterative optimization of geometry and textures. The project covers a broad r

    Python
    View on GitHub↗8,841
  • mrforexample/comfyui-3d-packMrForExample avatar

    MrForExample/ComfyUI-3D-Pack

    3,648View on GitHub↗

    ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts. The system includes a Gaussian splatting generator for creating high-fidelity volumetric 3D scene representations and a multi-view image generator to produce consistent image sets for reconstruction. It also features a single image 3D mesh tool to build geometry from a single 2D source. The toolset covers 3

    Pythoncomfycomfyuimachine-learning
    View on GitHub↗3,648
  • aaronjackson/vrnAaronJackson avatar

    AaronJackson/vrn

    4,515View on GitHub↗

    vrn is a 3D face reconstruction tool that generates three-dimensional volumetric representations of human faces from single two-dimensional images. It utilizes a volumetric convolutional neural network regression model to predict 3D volume data directly from image pixels. The system converts these volumetric predictions into 3D meshes through isosurface extraction and vertex coloring. It further applies realistic surface details by mapping two-dimensional image pixels onto the resulting 3D mesh using nearest-neighbor texture projection. The project provides capabilities for single-image dept

    MATLAB
    View on GitHub↗4,515
Compare all 30 related projects→

Frequently asked questions

What does facebookresearch/pifuhd do?

pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D image. It utilizes pixel-aligned implicit functions to map image pixels to 3D space, predicting surface occupancy and distance to create detailed geometry.

What are the main features of facebookresearch/pifuhd?

The main features of facebookresearch/pifuhd are: Human Reconstruction, Coordinate-Based Neural Representations, 2D-to-3D Feature Projections, Pixel-Aligned Implicit Functions, Image-to-Mesh Generation, Volumetric Mesh Extraction, Single-Image 3D Reconstructions, 3D Mesh Post-Processing.

Which projects share features with facebookresearch/pifuhd?

Projects with overlapping indexed features include: tencentarc/instantmesh — InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large… mrforexample/comfyui-3d-pack — ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a… ashawkey/stable-dreamfusion — This project is a diffusion-based 3D generator and image-to-3D reconstruction system. It translates natural language… aaronjackson/vrn — vrn is a 3D face reconstruction tool that generates three-dimensional volumetric representations of human faces from… apple/ml-sharp — ml-sharp is a neural radiance field framework designed for single-image 3D reconstruction. It uses a neural network to… tencent-hunyuan/hunyuan3d-2.1 — Hunyuan3D-2.1 is a generative 3D framework and image-to-3D pipeline that transforms single 2D images into textured 3D…