Projects sharing features with Wonder3D

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.

This project is an RGB-D image inpainting tool and framework for 3D photo reconstruction. It transforms single 2D images into 3D content by estimating monocular depth and synthesizing missing color and depth data to fill occluded regions. The system uses a layered depth image representation to manage scene boundaries and pixel connectivity. This allows for novel view synthesis, enabling the generation of videos that simulate motion parallax effects from different camera perspectives. The project covers a range of spatial modeling capabilities, including depth map estimation, disparity-based

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

openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms Structure from Motion data—specifically camera poses and sparse point clouds—into detailed 3D models consisting of dense point clouds and textured meshes. The project provides a sequence of processing stages to densify point clouds, generate 3D surface meshes, and apply photorealistic textures. It uses multi-view texture blending to map accurate colors onto reconstructed geometry and employs iterative refinement to optimize mesh details. The system includes capabilities for impo

This project is a framework for neural radiance fields used to synthesize three-dimensional environments from sets of two-dimensional images and camera poses. It functions as a volumetric rendering engine and scene synthesizer that optimizes neural representations of spatial volumes to generate novel views of complex 3D scenes. The system implements a coordinate encoding system that transforms spatial coordinates into high-dimensional space to capture high-frequency geometric details. It also includes a neural mesh extractor that converts trained radiance fields into triangle meshes via march

PRNet is a Python library for 3D facial reconstruction. It uses a deep learning regression model to predict 3D facial geometry and vertex colors from a single 2D input image to generate a textured mesh. The project provides tools for digital face swapping, allowing the replacement of a target face with a new image and blending textures to match the original pose. It also includes a framework for face texture swapping and blending to fit specific 3D poses. Additional capabilities cover facial analysis, including the detection and alignment of facial landmarks and the estimation of head pose a

ml-sharp is a neural radiance field framework designed for single-image 3D reconstruction. It uses a neural network to predict 3D geometry and appearance from a single photograph in a single feedforward pass. The system generates metric 3D scene representations and includes a real-time view synthesizer for producing high-resolution images of new viewpoints. It also features a camera trajectory renderer that creates video sequences by moving a virtual camera through the predicted 3D space. The project covers coordinate-based neural rendering, 3D Gaussian representation regression, and real-ti

3DDFA is a 3D face reconstruction tool that generates three-dimensional facial meshes and 68 structural landmarks from a single two-dimensional input image. The project provides utilities for estimating facial pose and depth maps to determine the orientation and position of a face. It includes a geometry exporter to save reconstructed facial shapes into standard file formats for use in external 3D modeling software. The software further covers automated face cropping using landmark-based and landmark-free identification methods, as well as the extraction of specialized mathematical represent

GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and tetrahedral meshes. It functions as an image-to-3D reconstructor and text-to-3D generator, utilizing a differentiable 3D renderer to produce realistic visual perspectives and material effects. The system enables the creation of 3D assets from single 2D images, point clouds, or descriptive text prompts. It features a latent space interpolator for creating smooth transitions between different 3D objects and supports the independent control of geometry and texture. The project cov

TripoSR is a single-image 3D reconstruction system that generates a high-quality textured mesh from one photograph in under half a second. It uses a feedforward neural network to process a single image through a transformer architecture, compressing the input into a compact latent vector that conditions the entire reconstruction pipeline. The system outputs a separate UV texture map with configurable resolution, replacing vertex colors for higher-quality surface detail. The project is built around an end-to-end differentiable pipeline that trains the entire reconstruction system from image in

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

Hunyuan3D-2.1 is a generative 3D framework and image-to-3D pipeline that transforms single 2D images into textured 3D geometries. It functions as an asset generator that produces high-quality 3D meshes and textures using a flow-matching system. The project includes a specialized synthesizer for creating photorealistic textures with physically based rendering properties. These tools allow for the simulation of metallic reflections and light interactions on generated models. The system covers 3D asset pipeline automation through a sequence of shape generation and mesh refinement. It also provi

Threestudio is a 3D generative AI framework designed to create three-dimensional assets from text prompts and images. It provides specialized pipelines for text-to-3D generation and image-to-3D reconstruction, utilizing a neural radiance field trainer to produce geometry and textures. The framework is distinguished by its support for hybrid geometry backends, including signed distance functions, tetrahedra grids, and volume grids. It employs score distillation sampling to guide the generation process and features a modular plugin system for loading custom modules and nodes. The system covers

SAM 3D Objects is a promptable foundation model that recovers 3D objects and human meshes from single images. It converts masked objects in a single photograph into full 3D models with pose, shape, texture, and layout, while also producing complete 3D human body meshes from the same input. The system integrates promptable segmentation to isolate objects and humans before reconstruction, then aligns the independently reconstructed 3D elements into a shared coordinate space. This enables scene-level understanding where multiple 3D reconstructions from the same image coexist in a common coordina

Instant Meshes is a 3D surface remesher and computational geometry tool designed to generate optimized polygonal grids over existing three-dimensional models. It functions as a field-aligned mesh generator that computes orientation and position fields to ensure the resulting mesh follows the geometric flow and contours of a target surface. The tool distinguishes itself through an interactive mesh editor that allows for the manual refinement of these mathematical fields. Users can employ brush tools to adjust orientation and position fields, steering the mesh topology in real time through iter

AlphaFold3 is a biomolecular structure prediction model and bioinformatics structural analysis tool. It uses a deep learning system to predict the three-dimensional shapes of proteins, DNA, RNA, and ligands. The system functions as a diffusion-based protein folding model that predicts the spatial coordinates of biomolecular atoms and interactions. It utilizes a GPU-accelerated inference pipeline to process genetic sequences and structural templates for molecular modeling. The project covers structural bioinformatics analysis and protein interaction modeling to determine the physical arrangem

TRELLIS is a 3D generative AI model and latent diffusion framework designed to transform natural language descriptions or reference images into textured 3D assets. It operates as a text-to-3D asset generator that utilizes structured latent representations to produce high-quality 3D meshes, Gaussians, and Radiance Fields. The system functions as a multi-format 3D decoder, converting internal representations into standard exchange formats such as GLB and PLY. It also serves as a 3D asset editing tool, enabling the modification of specific regions of generated objects through targeted text or im

WebODM is a photogrammetry software suite and drone image processing platform used to transform raw aerial photographs into spatial data. It functions as a geospatial mapping tool for generating georeferenced 2D maps, 3D point clouds, and digital elevation models. The system operates as a 3D mesh generator that converts overlapping aerial photos into textured models. It provides an aerial mapping workflow to produce precise outputs for geographic analysis and surveying through various photogrammetry engines. The platform includes capabilities for geospatial data visualization and the process

Neuralangelo is a neural surface reconstruction framework that transforms two-dimensional image sequences and multi-view photography into high-fidelity 3D meshes. It implements a pipeline for training neural radiance fields to represent complex scenes as digital geometry. The project utilizes a signed distance function for surface representation and multi-resolution hash encoding to capture both coarse and fine geometric details. It employs differentiable volume rendering and gradient-based eikonal regularization to ensure the learned distance functions remain physically plausible. The syste

libigl is a C++ geometry processing library used for analyzing and manipulating 3D triangle and tetrahedral meshes. It functions as a numerical linear algebra suite and a mesh manipulation framework, integrating a geometric deformation engine to implement rigid and polyharmonic transformations. The project is distinguished by its header-only library design and its implementation of specialized deformation techniques, including rigid-as-possible and polyharmonic shape deformation. It also provides a visualization tool for rendering surfaces and scalar fields with interactive scene controls and

This project is a neural network extension for Stable Diffusion that provides spatial control and geometric consistency for text-to-image generation. It functions as an image structure controller and conditioning tool, enabling the use of external inputs to guide the layout and geometry of generated imagery. The framework is distinguished by its ability to transform input images into structural guides through various preprocessors. These include the extraction of depth maps, normal maps, and human pose landmarks, as well as the detection of Canny edges, anime lineart, and straight architectur

This project is a diffusion model training framework and image synthesis pipeline. It provides the tools necessary to train generative models to learn image data distributions through an iterative denoising process. The framework includes a generative model evaluation tool consisting of automated scripts used to measure the quality and accuracy of produced samples. The system covers model training pipelines and performance evaluation for generative diffusion models.

gsplat is a high-performance differentiable rasterization engine for 3D Gaussian splatting, designed for real-time novel view synthesis from 2D images. It provides a complete pipeline for reconstructing 3D scenes by optimizing differentiable Gaussian representations, training models from COLMAP-processed captures or proprietary device files, and generating new viewpoints through a CUDA-accelerated rendering backend. The framework distinguishes itself through memory-optimized CUDA kernels that reduce training memory usage by up to 4x compared to standard implementations while matching publishe

This project is a cloud-based AI deployment system and latent diffusion model trainer. It provides a framework for launching image generation interfaces and training pipelines on remote GPU infrastructure, specifically serving as a text-to-image model fine-tuner. The system features a specialized training interface for fine-tuning Stable Diffusion models on custom image datasets. It allows for the creation of personalized visual outputs by training models on specific subjects or artistic styles using a small set of reference images. The software covers generative AI deployment, custom style

FastVideo is a comprehensive system for accelerated video generation, serving as a video generation inference engine, a video diffusion training framework, and a modular pipeline orchestrator. It provides a distributed transformer optimizer and a distillation toolkit designed to reduce denoising steps and model complexity to increase frame rates. The project distinguishes itself through specialized acceleration techniques, including joint distillation and sparse attention training. It implements low-step video generation and weight quantization to FP8 or FP4 precision to increase throughput a

This project is an educational course and collection of training materials focused on generative diffusion models. It provides a curriculum and practical guides for training, fine-tuning, and deploying models capable of synthesizing images, audio, and video. The material covers specific implementation strategies including noise-based synthesis, iterative refinement, and latent space compression. It provides instruction on guiding generative outputs through conditional synthesis and prompt adherence optimization, as well as techniques for image inpainting and text-based editing. The project i

This is a collection of Jupyter notebooks that serve as educational guides for training, fine-tuning, and deploying machine learning models within the Hugging Face ecosystem. The notebooks cover the full lifecycle of model development, from loading and configuring pre-trained transformers to packaging trained models for real-time inference via scalable endpoints. The notebooks demonstrate a range of capabilities including diffusion model training and fine-tuning for image generation and editing, transformer model adaptation for natural language processing tasks, and parameter-efficient fine-t