README.md

---
license: cc-by-4.0
language:
- en
pipeline_tag: robotics
tags:
- Grasping
- Manipulation
- IA
- Transformers
- CVAE
---

# **CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning** 

[Julien Mérand](https://julienmerand.github.io/portfolio/)<sup>1</sup>, &nbsp;&nbsp; [Boris Meden](https://scholar.google.com/citations?user=knXPf8oAAAAJ&hl=fr)<sup>1</sup>, &nbsp;&nbsp; [Liming Chen](https://scholar.google.com/citations?user=VOPW5YYAAAAJ&hl=fr)<sup>2</sup>, &nbsp;&nbsp; [Mathieu Grossard](mailto:mathieu.grossard@cea.fr)<sup>1</sup>

<sup>1</sup>Université Paris-Saclay, CEA-List &nbsp;&nbsp; <sup>2</sup>École Centrale de Lyon, CNRS, LIRIS, UMR5205, Institut Universitaire de France (IUF)

#### 19th European Conference on Computer Vision (ECCV 2026)

[**Project Page**](https://cea-list.github.io/cotograspweb/) &nbsp;&nbsp;|&nbsp;&nbsp; [**arXiv**](https://arxiv.org/abs/2608.19776)

**CoToGrasp** is a novel generative framework that synthesizes diverse and stable grasps strictly conditioned on specific contact topologies.


See [https://github.com/CEA-LIST/CoToGrasp](https://github.com/CEA-LIST/CoToGrasp) for full code and instructions.


Your directory tree should strictly follow this structure:
```bash
# Model Checkpoints
COTOGRASP                                           # Main folder
├── ...
├── logs                                            # ckpts folder
    ├── allegro_right_goag_dgcnn_types_2_0209
    └── shadowhand_goag_dgcnn_types_2_0128
└── ...

# Dataset Directory
COTOGRASP_DATA
├── handprints
├── pointclouds
    ├── dexgraspnet
    ├── multidex
        ├── contactdb
        └── ycb
├── urdf
    ├── objects
        ├── dexgraspnet
        ├── multidex
    └── robot
└── workspaces
```