AI tools for 3D Human Modeling

SafeNew is designed to bridge the gap between machine-generated text and authentic human expression. It specializes in transforming raw output from content generators into fluid

Artlist.io is an all-in-one subscription platform catering primarily to video creators, filmmakers, and social media content producers who require high-quality digital assets un

GNM, the Generative aNthropometric Model and Ecosystem from Google, is an open ecosystem for parametric human models and related perception stacks. The repository starts with GN

Actionable World Representation, presented through WorldString, is a method for building neural digital twins of physical objects. It learns token assignments and error maps fro

D-Rex is a diffusion-rendering framework for photorealistic, relightable, expressive full-body human avatars. It is designed for applications such as telepresence, gaming, virtu

UniSH is a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. It takes a monocular video as input and enables effective estimation of scen

SAM 3D is a powerful 3D reconstruction model that enables the creation of detailed 3D scenes from 2D images. This model is a significant step forward in leveraging large-scale r

PhysX-3D is an end-to-end paradigm for physical-grounded 3D asset generation. It aims to bridge the critical gap in physics-annotated 3D datasets by proposing PhysXNet, the firs

Diffuman4D is a novel approach to 4D consistent human view synthesis from sparse-view videos. It enables high-fidelity free-viewpoint rendering of human performances from sparse

LHM (Large Animatable Human Reconstruction Model) is a model for rapid, high-fidelity animatable 3D human reconstruction from a single image, decoupling geometry, appearance and

PicToMesh is a web-based platform that converts 2D images into detailed 3D models, aimed at creators, designers and game developers. Users upload images in PNG, JPG, JPEG or Web

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained entirely inside a diffusion world model, presented as a NeurIPS 2024 Spotlight by

MagicAnimate is an open-source, diffusion-based framework from Show Lab at the National University of Singapore and ByteDance that animates a static human image by transferring