# Deep Dexterous Grasping of Novel Objects from a Single View

arXiv: https://arxiv.org/abs/1908.04293 · HTML: https://mlsanity.com/paper/1908.04293/

## Key facts

- Cited by 4 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 10 Aug 2019.

## Built on by (most cited first, 4 of 4)

- [DDGC: Generative Deep Dexterous Grasping in Clutter](https://mlsanity.com/paper/2103.04783/) (2021)
- [CMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network](https://mlsanity.com/paper/2303.13182/) (2023)
- [EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows](https://mlsanity.com/paper/2606.12728/) (2026)
- [DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation](https://mlsanity.com/paper/2510.15786/) (2025)

## Abstract (arXiv)

Dexterous grasping of a novel object given a single view is an open problem. This paper makes several contributions to its solution. First, we present a simulator for generating and testing dexterous grasps. Second we present a data set, generated by this simulator, of 2.4 million simulated dexterous grasps of variations of 294 base objects drawn from 20 categories. Third, we present a basic architecture for generation and evaluation of dexterous grasps that may be trained in a supervised manner. Fourth, we present three different evaluative architectures, employing ResNet-50 or VGG16 as their visual backbone. Fifth, we train, and evaluate seventeen variants of generative-evaluative architectures on this simulated data set, showing improvement from 69.53% grasp success rate to 90.49%. Finally, we present a real robot implementation and evaluate the four most promising variants, executing 196 real robot grasps in total. We show that our best architectural variant achieves a grasp success rate of 87.8% on real novel objects seen from a single view, improving on a baseline of 57.1%.