# TARGO: Benchmarking Target-driven Object Grasping under Occlusions

arXiv: https://arxiv.org/abs/2407.06168 · HTML: https://mlsanity.com/paper/2407.06168/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 55 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Builds on (most cited first, 9 of 9)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter](https://mlsanity.com/paper/2101.01132/) (2021)
- [VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects](https://mlsanity.com/paper/2106.14440/) (2021)
- [pix2gestalt: Amodal Segmentation by Synthesizing Wholes](https://mlsanity.com/paper/2401.14398/) (2024)
- [Amodal Completion via Progressive Mixed Context Diffusion](https://mlsanity.com/paper/2312.15540/) (2023)
- [DynPoint: Dynamic Neural Point For View Synthesis](https://mlsanity.com/paper/2310.18999/) (2023)
- [A Tri-Layer Plugin to Improve Occluded Detection](https://mlsanity.com/paper/2210.10046/) (2022)
- [ICGNet: A Unified Approach for Instance-Centric Grasping](https://mlsanity.com/paper/2401.09939/) (2024)
- [TAO-Amodal: A Benchmark for Tracking Any Object Amodally](https://mlsanity.com/paper/2312.12433/) (2023)

## Built on by (most cited first, 3 of 3)

- [EGM: Efficient Visual Grounding Language Models](https://mlsanity.com/paper/2601.13633/) (2026)
- [Towards Explaining Uncertainty Estimates in Point Cloud Registration](https://mlsanity.com/paper/2412.20612/) (2024)
- [MessyKitchens: Contact-rich object-level 3D scene reconstruction](https://mlsanity.com/paper/2603.16868/) (2026)

## Abstract (arXiv)

Recent advances in predicting 6D grasp poses from a single depth image have led to promising performance in robotic grasping. However, previous grasping models face challenges in cluttered environments where nearby objects impact the target object's grasp. In this paper, we first establish a new benchmark dataset for TARget-driven Grasping under Occlusions, named TARGO. We make the following contributions: 1) We are the first to study the occlusion level of grasping. 2) We set up an evaluation benchmark consisting of large-scale synthetic data and part of real-world data, and we evaluated five grasp models and found that even the current SOTA model suffers when the occlusion level increases, leaving grasping under occlusion still a challenge. 3) We also generate a large-scale training dataset via a scalable pipeline, which can be used to boost the performance of grasping under occlusion and generalized to the real world. 4) We further propose a transformer-based grasping model involving a shape completion module, termed TARGO-Net, which performs most robustly as occlusion increases. Our benchmark dataset can be found at https://TARGO-benchmark.github.io/.