Research map / 3D vision / Depth and stereo
GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions
Haifeng Zhong, Wenshuo Han, Zhouyu Wang, Runyang Feng, Fan Tang, Tong-Yee Lee, Zipei Fan, Ruihai Wu, Yuran Wang, Hao Dong, Hechang Chen, Hyung Jin Chang and 1 more
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add parametric luminance curve (PLC) (ablation) | GraspALL · MIGG lum 0-40 | mGSR: 50.0% -> 88.3% | Improved |
| add parametric luminance curve (PLC) (ablation) | GraspALL · MIGG lum 0-40 | mIoU: 65.4% -> 82.6% | Improved |
| add luminance response library (LRL) (ablation) | GraspALL · MIGG lum 0-40 | mGSR: 72.5% -> 88.3% | Improved |
| add structural response library (SRL) (ablation) | GraspALL · MIGG lum 0-40 | mGSR: 57.5% -> 88.3% | Improved |
| add spectral consistency loss (ablation) | GraspALL · MIGG lum 0-40 | mGSR: 50.2% -> 88.3% | Improved |
| add binary cross-entropy structure loss (ablation) | GraspALL · MIGG lum 0-40 | mGSR: 70.4% -> 88.3% | Improved |
| use GraspALL instead of DarkSeg in extreme low light | GraspALL · MIGG grasping lum 0-40 | mGSR: 53.3% -> 84.2% | Improved |
| use GraspALL instead of MRFS across brightness | GraspALL · MIGG mask lum 90-120 vs 0-30 | mIoU: 76.2% -> 84.8%; 64.2% -> 82.8% | Improved |
| replace PLC by histogram mean luminance index (ablation) | GraspALL · Grad-CAM, unseen illumination | attention stability | Improved |
| use GraspALL instead of baselines in real world | GraspALL · real-world robot Lu 0-20 | grasp success: 7 / 15 -> 12 / 15 | Improved |
Closest papers by meaning
- GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation (CVPR 2025 · similarity 0.85)
- DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy (NeurIPS 2025 · similarity 0.84)
- UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence (CVPR 2024 · similarity 0.84)
- GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation (NeurIPS 2024 · similarity 0.83)
- Learning Efficient Robotic Garment Manipulation with Standardization (ICML 2025 · similarity 0.82)
- RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation (CVPR 2026 · similarity 0.82)
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.
