Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Physics-Guided Multistep Deformation Reversal for Ancient Bamboo Slip Restoration
Qianqian Tang, Jinchi Zhu, Xiaolu Zhou, Yongchao Xu
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 Force Balance (stress transfer) (ablation) | CreepDeformationEngine · synthetic test set | DCI: 2.884 -> 7.942 | Improved |
| add Fiber Elongation (ablation) | CreepDeformationEngine · synthetic test set | DCI: 3.213 -> 7.942 | Improved |
| add Fiber Elongation (ablation) | CreepDeformationEngine · synthetic test set | Straightness: 0.073 -> 0.296 | Improved |
| add Moisture Diffusion (ablation) | CreepDeformationEngine · synthetic test set | TRQ: 0.897 -> 1.018 | Improved |
| add Moisture Diffusion (ablation) | CreepDeformationEngine · synthetic test set | DCI: 6.115 -> 7.942 | Improved |
| add Fiber Elongation (ablation) | CreepDeformationEngine · synthetic test set | TRQ: 1.002 -> 1.018 | No clear effect |
| use physics-guided multistep reversal instead of DewarpNet | Bamboo slip restoration · synthetic test set | TRQ: 0.9651 -> 1.0176 | Improved |
| use physics-guided multistep reversal instead of DewarpNet | Bamboo slip restoration · real deformed slips | DCI: 6.273 -> 7.151 | Improved |
| use physics-guided method instead of DDRM | Bamboo slip restoration · synthetic test set | Straightness: 0.3476 -> 0.2962 | Hurt |
| use physics-guided method instead of CycleGAN | Bamboo slip restoration · synthetic test set | LPIPS: 0.1184 -> 0.2315 | Hurt |
Closest papers by meaning
- Virtual Restoration of Ancient Wooden Ships Through Non-rigid 3D Shape Assembly with Ruled-Surface FFD (IJCV 2023 · similarity 0.83)
- Towards Automated Chinese Ancient Character Restoration: A Diffusion-Based Method with a New Dataset (AAAI 2024 · similarity 0.79)
- UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation (CVPR 2025 · similarity 0.79)
- Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving (NeurIPS 2024 · similarity 0.78)
- Training-Free Constrained Generation With Stable Diffusion Models (NeurIPS 2025 · similarity 0.78)
- InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences (ICLR 2025 · similarity 0.78)
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.
