Research map / Optimization / Optimizers
GFPack++: Attention-Driven Gradient Fields for Optimizing 2D Irregular Packing
Tianyang Xue, Lin Lu, Yang Liu, Mingdong Wu, Hao Dong, Yanbin Zhang, Renmin Han, Baoquan Chen
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 utilization enhancement (constraint gradient + gap elimination) (ablation) | GFPack++ · Garment | avg packing utilization (%): 74.25 -> 77.04 | Improved |
| add utilization enhancement (ablation) | GFPack++ · Dental | avg packing utilization (%): 75.11 -> 77.53 | Improved |
| add utilization enhancement (ablation) | XAtlas · Garment | avg packing utilization (%): 68.90 -> 69.53 | No clear effect |
| add utilization enhancement (ablation) | SVGnest · Dental | avg packing utilization (%): 72.55 -> 73.64 | No clear effect |
| train with arbitrary rotations (R) and enhancement | GFPack++ · Dental (GFPack comparison) | avg packing utilization (%): 73.93 -> 77.53 | Improved |
| increase batch size from 128 to 512 | GFPack++ · Garment | avg packing utilization (%): 74.22 -> 77.04 | Improved |
| increase batch size from 128 to 512 | GFPack++ · Dental (alphabet) generalization | valid solutions (%): 38.53 -> 67.54 | Improved |
| replace GFPack with GFPack++ architecture | GFPack · Garment (GFPack comparison) | avg packing utilization (%): 69.82 -> 74.25 | Improved |
| use GFPack++ relation encoder with GFPack geometric encoder (ablation) | GFPack · Dental (encoder ablation) | overlap area (%): 13.2 -> 1.89 | Improved |
| use GFPack++ geometric encoder instead of AvgPool (ablation) | GFPack++ · Dental (encoder ablation) | overlap area (%): 0.85 -> 0.08 | Improved |
| use GFPack++ geometric encoder instead of GFPack geometric encoder (ablation) | GFPack++ · Dental (encoder ablation) | avg packing utilization (%): 72.84 -> 74.25 | Improved |
| quadruple GFPack parameters from 10M to 40M | GFPack · Dental with rotations | feasibility | No clear effect |
Closest papers by meaning
- RASP: Revisiting 3D Anamorphic Art for Shadow-Guided Packing of Irregular Objects (CVPR 2025 · similarity 0.83)
- DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly (CVPR 2024 · similarity 0.82)
- G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping (CVPR 2024 · similarity 0.82)
- Diffeomorphic interpolation for efficient persistence-based topological optimization (NeurIPS 2024 · similarity 0.82)
- PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction (CVPR 2025 · similarity 0.81)
- ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems (ICML 2025 · similarity 0.81)
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.
