# A Robotic Visual Grasping Design: Rethinking Convolution Neural Network with High-Resolutions

arXiv: https://arxiv.org/abs/2209.07459 · HTML: https://mlsanity.com/paper/2209.07459/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 15 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours](https://mlsanity.com/paper/1509.06825/) (2015)
- [Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach](https://mlsanity.com/paper/1804.05172/) (2018)
- [Deep Learning for Detecting Robotic Grasps](https://mlsanity.com/paper/1301.3592/) (2013)
- [Jacquard: A Large Scale Dataset for Robotic Grasp Detection](https://mlsanity.com/paper/1803.11469/) (2018)
- [Real-Time Grasp Detection Using Convolutional Neural Networks](https://mlsanity.com/paper/1412.3128/) (2014)
- [Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network](https://mlsanity.com/paper/1909.04810/) (2019)
- [Robotic Grasp Detection using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1611.08036/) (2016)
- [End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB](https://mlsanity.com/paper/2107.05287/) (2021)
- [ROI-based Robotic Grasp Detection for Object Overlapping Scenes](https://mlsanity.com/paper/1808.10313/) (2018)
- [Fully Convolutional Grasp Detection Network with Oriented Anchor Box](https://mlsanity.com/paper/1803.02209/) (2018)
- [Multi-View Picking: Next-best-view Reaching for Improved Grasping in Clutter](https://mlsanity.com/paper/1809.08564/) (2018)
- [Places205-VGGNet Models for Scene Recognition](https://mlsanity.com/paper/1508.01667/) (2015)
- [When Transformer Meets Robotic Grasping: Exploits Context for Efficient Grasp Detection](https://mlsanity.com/paper/2202.11911/) (2022)
- [GQ-STN: Optimizing One-Shot Grasp Detection based on Robustness Classifier](https://mlsanity.com/paper/1903.02489/) (2019)
- [Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection](https://mlsanity.com/paper/2101.10226/) (2021)

## Built on by (most cited first, 2 of 2)

- [WorldAfford: Affordance Grounding based on Natural Language Instructions](https://mlsanity.com/paper/2405.12461/) (2024)
- [HMT-Grasp: A Hybrid Mamba-Transformer Approach for Robot Grasping in Cluttered Environments](https://mlsanity.com/paper/2410.03522/) (2024)

## Abstract (arXiv)

High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution representations. This will lose spatial information, and errors introduced by the decoder will be more serious when multiple types of objects are considered or objects are far away from the camera. To address these issues, we revisit the design paradigm of CNN for robotic perception tasks. We demonstrate that using parallel branches as opposed to serial stacked convolutional layers will be a more powerful design for robotic visual grasping tasks. In particular, guidelines of neural network design are provided for robotic perception tasks, e.g., high-resolution representation and lightweight design, which respond to the challenges in different manipulation scenarios. We then develop a novel grasping visual architecture referred to as HRG-Net, a parallel-branch structure that always maintains a high-resolution representation and repeatedly exchanges information across resolutions. Extensive experiments validate that these two designs can effectively enhance the accuracy of visual-based grasping and accelerate network training. We show a series of comparative experiments in real physical environments at Youtube: https://youtu.be/Jhlsp-xzHFY.