AI Paper Atlas

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

AAAI 2026 · 3D vision › 3D generation · approach: Learning physics from video · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add piecewise topology solution (ablation)PhysTwin baseline · PhysTwin dataset, future predictionCD: 0.0118 -> 0.0114Improved
add neural spring field (ablation)PhysTwin baseline · PhysTwin dataset, future predictionCD: 0.0118 -> 0.0101Improved
add both modules (ablation)PhysTwin baseline · PhysTwin dataset, future predictionCD: 0.0118 -> 0.0087Improved
add both modules (ablation)PhysTwin baseline · PhysTwin dataset, reconstruction & resimulationCD: 0.0054 -> 0.0043Improved
add piecewise topology solution (ablation)PhysTwin baseline · PhysTwin dataset, future predictionIoU (%): 70.2 -> 72.3Improved
add neural spring field alone (ablation)PhysTwin baseline · PhysTwin dataset, reconstruction & resimulationIoU (%): 83.5 -> 83.9; LPIPS 0.035 -> 0.034Mixed
add tri-plane representation (ablation)neural spring field · PhysTwin dataset, future predictionCD: 0.0112 -> 0.0087Improved
add adaptive tri-plane resolution (ablation)neural spring field · PhysTwin dataset, future predictionCD: 0.0095 -> 0.0087Improved
add adaptive tri-plane resolution (ablation)neural spring field · PhysTwin dataset, reconstruction & resimulationCD: 0.0045 -> 0.0043Improved
use more topology clusters (ablation)piecewise topology solution · two scenariosCDImproved
full method vs PhysTwin (ablation)NeuSpring · PhysTwin dataset, future predictionCD: 0.012 -> 0.009Improved
full method vs PhysTwin (ablation)NeuSpring · PhysTwin dataset, reconstruction & resimulationCD: 0.005 -> 0.004Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy