Open-source alternatives to InstantMesh

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.

Modly is a local AI 3D model generator that converts two-dimensional images into three-dimensional meshes. It is a privacy-focused tool that processes data directly on the host graphics card using GPU-accelerated inference. The system serves as an extensible AI model framework, allowing the integration of external model extensions and runtime files from remote repositories. It utilizes a manifest-driven plugin architecture to add new generation methods by loading metadata and files from external version control systems. The toolset includes a command-line interface for triggering generation

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

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

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

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

TRELLIS.2 is a generative image-to-3D system that creates high-resolution 3D assets with physically based rendering materials from 2D images. It utilizes a sparse voxel representation to handle complex topologies and internal structures without relying on iso-surface fields. The project features a structured latent space representation that maps geometry and texture attributes to maintain visual fidelity. It employs an optimization-free geometry reconstruction process to decode latent representations directly into voxel grids and includes a PBR texture generator for synthesizing base color, r

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

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

Map-anything is a 3D scene reconstruction framework and neural geometry estimator designed to transform two-dimensional images into metric three-dimensional spatial representations using feed-forward neural networks. It provides a specialized toolkit for predicting camera intrinsics and ray directions from single images without requiring external geometric metadata. The project includes a 3D model benchmarking suite that utilizes a unified model wrapper to standardize outputs from diverse reconstruction models. This allows for consistent evaluation and accuracy measurement across various spat

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

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

This project is a PyTorch implementation of a Neural Radiance Field framework. It serves as a 3D scene synthesizer and differentiable volumetric renderer used to train volumetric representations of scenes by predicting color and density for 3D spatial coordinates. The system enables novel view synthesis, allowing for the generation of new images of complex 3D scenes from previously unseen perspectives. It supports 3D scene reconstruction by processing 2D images and camera poses to build a digital volumetric representation of a physical space. The framework includes capabilities for 3D model

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

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

DreamGaussian is a generative system and converter designed to create textured three-dimensional models from text or images using Gaussian Splatting. It functions as a pipeline for transforming two-dimensional inputs into high-fidelity 3D assets. The project provides specific workflows for converting 3D Gaussian point clouds into standard textured mesh formats compatible with external 3D software. It supports the generation of textured meshes from single images via volumetric refinement and UV texture optimization, as well as the creation of 3D models from text prompts through intermediate im

Neural renderer is a differentiable rendering library for PyTorch that projects three-dimensional meshes into two-dimensional images while maintaining continuous mathematical gradients for backpropagation. The framework enables gradient-based inverse rendering, allowing optimization of input parameters such as camera pose, vertex positions, and texture maps by propagating pixel-level reconstruction errors backward to the source geometry. The architecture incorporates approximate rasterisation gradients that substitute discontinuous edge derivatives with heuristic approximations to facilitate

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

COLMAP is a 3D scene reconstruction suite and C++ geometry library that implements a full structure-from-motion pipeline. It functions as a GPU-accelerated photogrammetry tool and multi-view stereo framework designed to produce dense 3D geometry and watertight meshes from collections of 2D images. The project distinguishes itself through hardware-accelerated feature extraction and a modular camera modeling system that supports perspective, fisheye, and equirectangular lens types. It employs vocabulary tree image retrieval to efficiently identify similar images in large datasets and provides P

Terrain3D is a high-performance toolkit for creating, sculpting, and painting editable 3D landscapes within the Godot game engine. It provides a set of tools for generating landmasses and converting external geography data into optimized 3D terrain meshes. The system features a foliage manager that places vegetation across landscapes using levels of detail and shadow impostors to maintain performance. It also includes a sculpting tool that supports the creation of landmasses with holes and multi-layered texture painting. The project covers a broad capability surface including heightmap impor

Wonder3D is a diffusion-based system for single image 3D reconstruction. It generates high-detail 3D meshes from a single input image by producing consistent multi-view normal maps and color images. The pipeline functions as a multi-view normal map generator and a textured mesh extractor. It uses cross-domain multi-view synthesis to create view-dependent maps, which are then converted into 3D geometry through radiance fusion and memory-efficient surface reconstruction. The project covers 3D mesh generation, multi-view generation, and textured 3D modeling. It also includes capabilities for tr

Hunyuan3D-2 is a machine learning framework designed to convert two-dimensional images into fully realized, textured three-dimensional meshes. It utilizes a generative artificial intelligence model to perform both shape construction and surface texture synthesis, enabling the automated creation of digital assets. The system distinguishes itself through a modular generative pipeline that separates geometry reconstruction from texture mapping. It employs multi-view image projection and latent diffusion techniques to ensure geometric consistency, while providing a plugin-based bridge architectur

Point-e is a system for 3D model synthesis that generates three-dimensional point clouds from natural language descriptions and two-dimensional images. It utilizes diffusion models to synthesize these spatial representations based on text prompts or source images. The project includes specialized tools for refining these outputs, such as a point cloud upsampler to increase the density and resolution of low-resolution models. It also provides a mesh converter that uses distance function regression to transform raw point cloud data into structured 3D meshes. The broader capability surface cove

A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷

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

Kaolin is a PyTorch 3D deep learning library providing a comprehensive suite of tools for 3D geometry processing, physics simulation, data visualization, and gradient-based rendering for computer vision. The library includes a differentiable 3D renderer and a geometry processing toolkit for converting and transforming 3D representations such as meshes and point clouds. It also features a 3D physics simulation engine to calculate physical interactions and collisions between three-dimensional objects and scenes. The toolkit provides utilities for 3D data visualization, including the creation o

PyTorch3D is a 3D geometric deep learning library and mesh processing toolkit designed for learning from point clouds and complex 3D surface geometries. It provides a collection of reusable components and data structures for deep learning with 3D data, including a framework for training and evaluating neural radiance fields to enable photorealistic view synthesis. The project features a differentiable 3D renderer that converts meshes and point clouds into 2D images while allowing gradients to flow back into the geometry and textures. This enables 3D shape optimization, where mesh geometry, te