AI Paper Atlas

Research map / 3D vision / Human pose estimation

TARGO and TARGO-Net: Benchmarking Target-Driven Object Grasping Under Occlusions

Yan Xia, Ran Ding, Ziyuan Qin, Guanqi Zhan, Kaichen Zhou, Long Yang, Hao Dong, Daniel Cremers

IJCV 2026 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add shape completion module of the target (ablation)TARGO-Net · TARGO-Synthetic, occlusion above 0.4grasp success rate: up to 18% decrease without itImproved
use completed target and completed target scene instead of partial target and raw scene (ablation)TARGO-Net · TARGO-Synthetic, high occlusiongrasp success rate: approximately 20% drop for PT with RS after [0.4, 0.5)Improved
use completed target (CT) with completed scene instead of partial target with CTS (ablation)TARGO-Net · TARGO-Synthetic, high occlusiongrasp success rate: about 10% decline with partial target; about 12% decline with raw sceneImproved
add single-scene data augmentation to training (ablation)VGN, GIGA-Aff and TARGO-Net · TARGO-Synthetic testgrasp success rateImproved
use shape completion instead of scene completionTARGO-Net vs GIGA · TARGO-Synthetic target completionChamfer L1 (x1000): 8.722 -> 2.443Improved
use shape completion instead of scene completionTARGO-Net vs GIGA · TARGO-Synthetic target completionIoU (%): 78.77 -> 93.99Improved
use cross-attention Transformer backbone instead of 3D CNN with concat or add fusion (ablation)TARGO-Net w/o SC · TARGO-Synthetic, Gaussian noise sigma 0.005grasp success rate: 2% better than second best, 5% better than worstImproved
use two cross-attention Transformer layers instead of one or three (ablation)TARGO-Net · TARGO-Synthetic testgrasp success rateImproved
switch from simulation to real-world testTARGO-Net · Real-world vs simulation, high occlusiongrasp success rate drop: 7% -> 14%Hurt
replace GIGA with TARGO-Netreal-world grasping · Real-world Hard occlusion [0.6,0.9)grasp success rate (%): 30.0 -> 66.7Improved
increase number of occluders from 2 to 6GIGA · TARGO-Synthetic, occlusion [0.7, 0.8)grasp success rate: decreases by 15%Hurt
increase number of occluders from 2 to 6TARGO-Net · TARGO-Synthetic, occlusion [0.2, 0.3)grasp success rate: increases by 14%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy