# GNOCHI: Generative Neural mOdel for Close Human-Human Interactions

arXiv: https://arxiv.org/abs/2607.10408 · HTML: https://mlsanity.com/paper/2607.10408/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 52 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 30 of 38)

- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Populating 3D Scenes by Learning Human-Scene Interaction](https://mlsanity.com/paper/2012.11581/) (2020)
- [GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB](https://mlsanity.com/paper/1712.01057/) (2017)
- [GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping](https://mlsanity.com/paper/2112.11454/) (2021)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Decoupling Human and Camera Motion from Videos in the Wild](https://mlsanity.com/paper/2302.12827/) (2023)
- [Scaling Up Dynamic Human-Scene Interaction Modeling](https://mlsanity.com/paper/2403.08629/) (2024)
- [D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions](https://mlsanity.com/paper/2112.03028/) (2021)
- [Synthesizing Diverse Human Motions in 3D Indoor Scenes](https://mlsanity.com/paper/2305.12411/) (2023)
- [Inter-X: Towards Versatile Human-Human Interaction Analysis](https://mlsanity.com/paper/2312.16051/) (2023)
- [CHORE: Contact, Human and Object REconstruction from a single RGB image](https://mlsanity.com/paper/2204.02445/) (2022)
- [On Self-Contact and Human Pose](https://mlsanity.com/paper/2104.03176/) (2021)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [Compositional Human-Scene Interaction Synthesis with Semantic Control](https://mlsanity.com/paper/2207.12824/) (2022)
- [Full-Body Articulated Human-Object Interaction](https://mlsanity.com/paper/2212.10621/) (2022)
- [Multi-Person Extreme Motion Prediction](https://mlsanity.com/paper/2105.08825/) (2021)
- [DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras](https://mlsanity.com/paper/2105.00261/) (2021)
- [COAP: Compositional Articulated Occupancy of People](https://mlsanity.com/paper/2204.06184/) (2022)
- [InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling](https://mlsanity.com/paper/2410.10010/) (2024)
- [Generative Proxemics: A Prior for 3D Social Interaction from Images](https://mlsanity.com/paper/2306.09337/) (2023)
- [G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis](https://mlsanity.com/paper/2404.12383/) (2024)
- [Interaction Transformer for Human Reaction Generation](https://mlsanity.com/paper/2207.01685/) (2022)
- [FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis](https://mlsanity.com/paper/2405.15763/) (2024)
- [Simulation and Retargeting of Complex Multi-Character Interactions](https://mlsanity.com/paper/2305.20041/) (2023)
- [Reconstructing People, Places, and Cameras](https://mlsanity.com/paper/2412.17806/) (2024)

## Abstract (arXiv)

Creating realistic 3D human-human interactions in virtual environments is challenging due to the high degrees of freedom in the human body and the need for physically accurate poses that do not collide with each other. Traditional methods for human-human interaction are based on motion tracking or 3D body reconstruction, but lack generative capabilities. Recent generative methods enable the synthesis of individual or interacting motions via text or image input, but generally fall short in modeling close interactions. This paper introduces a novel generative model for close 3D human-human interactions using a conditional variational autoencoder (cVAE), which generates poses for one human conditioned on the pose of another, allowing for controlled and diverse interaction synthesis. To train our model, we address two underlying long-standing challenges in the field of human-human interaction: data scarcity, for which we propose an automated supervised data augmentation strategy that generates synthetic yet realistic interaction poses; and collision awareness in generative approaches, for which we propose a self-supervised loss based on a collision resolution technique using volumetric proxies to ensure physically correct interactions. We extensively evaluate the capabilities of our model, and demonstrate a wide variety of plausible and physically correct interactions, not possible to generate with current state-of-the-art methods.