Research map / Image generation / Fast diffusion sampling
FlowPalm: Optical Flow Driven Non-Rigid Deformation for Geometrically Diverse Palmprint Generation
Yuchen Zou, Huikai Shao, Lihuang Fang, Zhipeng Xiong, Dexing Zhong
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 deformation selection (filtering invalid warps) (ablation) | FlowPalm · avg 6 datasets, w/o Aug. | TAR@FAR=1e-6: 51.73 -> 58.95 | Improved |
| add deformation selection (filtering invalid warps) (ablation) | FlowPalm · avg 6 datasets, w/ Aug. | TAR@FAR=1e-6: 76.61 -> 85.20 | Improved |
| add crease warping alongside noise warping (ablation) | FlowPalm · avg 6 datasets, w/o Aug. | TAR@FAR=1e-6: 27.43 -> 58.95 | Improved |
| add crease warping alongside noise warping (ablation) | FlowPalm · avg 6 datasets, w/ Aug. | TAR@FAR=1e-6: 71.00 -> 85.20 | Improved |
| add noise warping alongside crease warping (ablation) | FlowPalm · avg 6 datasets, w/o Aug. | TAR@FAR=1e-6: 7.58 -> 58.95 | Improved |
| add noise warping alongside crease warping (ablation) | FlowPalm · avg 6 datasets, w/ Aug. | TAR@FAR=1e-6: 74.08 -> 85.20 | Improved |
| add all three deformation components (ablation) | FlowPalm · avg 6 datasets, w/o Aug. | TAR@FAR=1e-6: 7.78 -> 58.95 | Improved |
| add all three deformation components (ablation) | FlowPalm · avg 6 datasets, w/ Aug. | TAR@FAR=1e-6: 74.78 -> 85.20 | Improved |
| add unconditional texture refinement (tau_u 0.00 -> 0.25) (ablation) | FlowPalm · avg 6 datasets, w/o Aug. | TAR@FAR=1e-6: 29.89 -> 58.95 | Improved |
| add unconditional texture refinement (tau_u 0.00 -> 0.25) (ablation) | FlowPalm · avg 6 datasets, w/ Aug. | TAR@FAR=1e-6: 67.25 -> 85.20 | Improved |
| raise drop time tau_u from 0.25 to 0.30 (ablation) | FlowPalm · avg 6 datasets, w/o Aug. | TAR@FAR=1e-6: 58.95 -> 58.57 | No clear effect |
| add deformations (non-rigid) vs rigid intra-class: Fréchet Distance with all components (ablation) | FlowPalm · Fréchet Distance | Fréchet Distance: 0.1663 -> 0.1503 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PCE-Palm — PCE-Palm: Palm Crease Energy Based Two-Stage Realistic Pseudo-Palmprint Generation (AAAI 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models (CVPR 2025 · similarity 0.88)
- BézierPalm: A Free Lunch for Palmprint Recognition (ECCV 2022 · similarity 0.88)
- PCE-Palm: Palm Crease Energy Based Two-Stage Realistic Pseudo-Palmprint Generation (AAAI 2024 · similarity 0.87)
- PVTree: Realistic and Controllable Palm Vein Generation for Recognition Tasks (AAAI 2025 · similarity 0.84)
- Towards Explainable and Unprecedented Accuracy in Matching Challenging Finger Crease Patterns (CVPR 2025 · similarity 0.81)
- FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generation (CVPR 2025 · similarity 0.80)
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.
