Research map / 3D vision / 3D generation
NeuSpring: Neural Spring Fields for Reconstruction and Simulation of Deformable Objects from Videos
Qingshan Xu, Jiao Liu, Shangshu Yu, Yuxuan Wang, Yuan Zhou, Junbao Zhou, Jiequan Cui, Yew-Soon Ong, Hanwang Zhang
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 piecewise topology solution (ablation) | PhysTwin baseline · PhysTwin dataset, future prediction | CD: 0.0118 -> 0.0114 | Improved |
| add neural spring field (ablation) | PhysTwin baseline · PhysTwin dataset, future prediction | CD: 0.0118 -> 0.0101 | Improved |
| add both modules (ablation) | PhysTwin baseline · PhysTwin dataset, future prediction | CD: 0.0118 -> 0.0087 | Improved |
| add both modules (ablation) | PhysTwin baseline · PhysTwin dataset, reconstruction & resimulation | CD: 0.0054 -> 0.0043 | Improved |
| add piecewise topology solution (ablation) | PhysTwin baseline · PhysTwin dataset, future prediction | IoU (%): 70.2 -> 72.3 | Improved |
| add neural spring field alone (ablation) | PhysTwin baseline · PhysTwin dataset, reconstruction & resimulation | IoU (%): 83.5 -> 83.9; LPIPS 0.035 -> 0.034 | Mixed |
| add tri-plane representation (ablation) | neural spring field · PhysTwin dataset, future prediction | CD: 0.0112 -> 0.0087 | Improved |
| add adaptive tri-plane resolution (ablation) | neural spring field · PhysTwin dataset, future prediction | CD: 0.0095 -> 0.0087 | Improved |
| add adaptive tri-plane resolution (ablation) | neural spring field · PhysTwin dataset, reconstruction & resimulation | CD: 0.0045 -> 0.0043 | Improved |
| use more topology clusters (ablation) | piecewise topology solution · two scenarios | CD | Improved |
| full method vs PhysTwin (ablation) | NeuSpring · PhysTwin dataset, future prediction | CD: 0.012 -> 0.009 | Improved |
| full method vs PhysTwin (ablation) | NeuSpring · PhysTwin dataset, reconstruction & resimulation | CD: 0.005 -> 0.004 | Improved |
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.
- PhysTwin — PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos (ICCV 2025) · better on 8 of 8 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
- DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos (NeurIPS 2026 · similarity 0.89)
- PhySPRING: Structure-Preserving Reduction of Physics-Informed Digital Twins via Graph Neural Networks (NeurIPS 2026 · similarity 0.87)
- NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory (NeurIPS 2024 · similarity 0.86)
- TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene (NeurIPS 2024 · similarity 0.85)
- UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation (CVPR 2025 · similarity 0.85)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.85)
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.
