--- title: README emoji: 🕺 colorFrom: indigo colorTo: green sdk: static pinned: false --- # EquiFusion **Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion** (ECCV 2026) EquiFusion predicts diverse realistic futures from a given input past and supports **any human skeleton or kinematics**. Instead of converting or unifying skeletons of different formats or training a new instance for every skeleton type, we adopt an orthogonal solution: create a model that supports them all. We give the skeleton kinematic tree as input to the model together with the past motion, so a single model instance forecasts the future across different datasets and skeleton formats, also zero-shot on skeletons unseen during training and on observations with missing limbs or joints. [Paper](https://arxiv.org/abs/2607.10984) · [Code](https://github.com/Ceveloper/EquiFusion) · [Project page](https://ceveloper.github.io/publications/equifusion/) · [Demo](https://huggingface.co/spaces/ceccurr/EquiFusion) ## Models | Model | Training data | Use | |---|---|---| | [equifusion-cross-kinematics-amass-nymeria](https://huggingface.co/EquiFusion/equifusion-cross-kinematics-amass-nymeria) | AMASS + Nymeria | main model; zero-shot on other skeletons | | [equifusion-cross-kinematics-amass-nymeria-h36m](https://huggingface.co/EquiFusion/equifusion-cross-kinematics-amass-nymeria-h36m) | AMASS + Nymeria + H36M | trained on three datasets | | [equifusion-cross-kinematics-amass](https://huggingface.co/EquiFusion/equifusion-cross-kinematics-amass) | AMASS | zero-shot on unseen skeletons | | [equifusion-cross-kinematics-amass-nymeria-3d](https://huggingface.co/EquiFusion/equifusion-cross-kinematics-amass-nymeria-3d) | AMASS + Nymeria | 3D joint representation, arbitrary missing joints | | [equifusion-in-domain-amass](https://huggingface.co/EquiFusion/equifusion-in-domain-amass) | AMASS | same-dataset evaluation | | [equifusion-in-domain-nymeria](https://huggingface.co/EquiFusion/equifusion-in-domain-nymeria) | Nymeria | same-dataset evaluation | | [equifusion-in-domain-h36m](https://huggingface.co/EquiFusion/equifusion-in-domain-h36m) | H36M | same-dataset evaluation | See the [code repository](https://github.com/Ceveloper/EquiFusion) for installation, inference, evaluation and training. ## Citation ```bibtex @inproceedings{curreli2026equifusion, title = {EquiFusion: Kinematics-Agnostic Human Motion Prediction via Equivariant Latent Diffusion}, author = {Curreli, Cecilia and Hofherr, Florian and Muhle, Dominik and Saroha, Abhishek and Marin, Riccardo and Cremers, Daniel}, booktitle = {European Conference on Computer Vision}, organization = {Springer}, year = {2026} } ```