VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions

TL;DR: VolumetricSMPL is a lightweight extension that adds volumetric capabilities to SMPL(-X) models for efficient 3D interactions and collision detection.

Key Features

Single-line integration with existing SMPL models
Fast and differentiable SDF queries
Built-in collision detection and self-intersection resolution
Compatible with SMPL, SMPLH, and SMPL-X

Watch the Overview

Read the Paper

Quick Start

VolumetricSMPL is a lightweight, plug-and-play extension for SMPL(-X) models that adds volumetric functionality via Signed Distance Fields (SDFs). With minimal integration—just a single line of code—users gain access to fast and differentiable SDF queries, collision detection, and self-intersection resolution. The model is fully compatible with existing SMPL-based pipelines and enables efficient interaction modeling in both perception and reconstruction tasks.

Installation

Here is a minimal example showing how to extend an existing smplx package with volumetric functionalities using VolumetricSMPL. First, install VolumetricSMPL via pip:

                    pip install VolumetricSMPL
                  

Usage Example

Then, extend an existing smplx model with volumetric functionalities using VolumetricSMPL:

Note: Make sure to install smplx and PyTorch3D first.

For more further experiments and use cases, check out our Applications repository.

BibTex

@inproceedings{ICCV25:VolumetricSMPL,
   title={{VolumetricSMPL}: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions},
   author={Mihajlovic, Marko and Zhang, Siwei and Li, Gen and Zhao, Kaifeng and M{\"u}ller, Lea and Tang, Siyu},
   booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
   year={2025}
}