SMPLer-X

Visit Tool

SMPLer-X is an open-source AI tool that scales up expressive human pose and shape estimation. It provides official code for training, testing, and inference, with support for Docker.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is SMPLer-X?

SMPLer-X is an open-source AI tool designed for scaling up expressive human pose and shape estimation, as featured in NeurIPS 2023. It offers official code for comprehensive human pose and shape estimation, including functionalities for training, testing, and inference. The tool supports various pretrained models with different backbones and parameters, such as ViT-S, ViT-B, ViT-L, and ViT-H, optimized for performance across multiple benchmarks. SMPLer-X also provides Docker support for inference, simplifying deployment. An updated version, SMPLest-X, extends its capabilities with stronger foundation models, further enhancing its utility for researchers and developers in the field of 3D human reconstruction.

Best used for

Ideal for developers and data scientists who need to accurately estimate human pose and shape from various data sources, train custom models, and visualize 3D human reconstructions. Especially valuable for research in computer vision, robotics, and creating applications that require detailed human body analysis.

Common actions

estimate human pose

estimate human shape

train 3D models

visualize 3D humans

github copilotface swapping"AI Agents"low-code/no-codedeepfakeopen-sourcecollaborationworkflowsautomated workflow

Capabilities

Key features

Human pose estimation
Shape estimation
Pretrained models
Docker support
Training code
Testing code
Mesh overlay visualization

Target Audience

developerdata scientist

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What is the primary difference between SMPLer-X and SMPLest-X?

SMPLest-X is an extension of SMPLer-X, offering stronger foundation models and an updated codebase for enhanced training, testing, and inference capabilities. It represents a further scaling up of expressive human pose and shape estimation, building upon the original SMPLer-X framework.

What kind of data is required to use SMPLer-X?

SMPLer-X requires various datasets for training and inference, including 3DPW, AGORA, EgoBody, UBody, and others. Users need to download and process these datasets into a HumanData format, and also prepare pretrained ViTPose models and SMPL-X body models.

Can SMPLer-X be used for real-time inference?

SMPLer-X provides pretrained models with varying inference speeds (FPS) on a single Tesla V100 GPU, ranging from 17.47 to 36.17 FPS depending on the model backbone. This indicates its capability for near real-time or real-time applications, especially with optimized hardware.

Trending

Subcategories trending in Content & Design

Image Generation AI Writing Assistants Audio & Music Video Generation Photo Editing Graphic Design

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce