Research map / 3D vision / 3D generation
Toward Material-Agnostic System Identification from Videos
Yizhou Zhao, Haoyu Chen, Chunjiang Liu, Zhenyang Li, Charles Herrmann, Junhwa Hur, Yinxiao Li, Ming-Hsuan Yang, Bhiksha Raj, Min 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 trajectory-based dense geometric loss instead of no geometric loss (ablation) | MASIV · PAC-NeRF future state (mean) | Chamfer Distance: 1755.635 -> 0.294 | Improved |
| replace surface loss with trajectory loss (ablation) | MASIV · PAC-NeRF future state (mean) | Chamfer Distance: 3593.608 -> 0.294 | Improved |
| replace continuum loss with trajectory loss (ablation) | MASIV · PAC-NeRF future state (mean) | Chamfer Distance: 0.308 -> 0.294 | Improved |
| add silhouette loss (ablation) | MASIV · PAC-NeRF observable state (mean) | Chamfer Distance: 0.926 -> 0.210 | Improved |
| fine-tune Jelly pre-trained constitutive model with MASIV (ablation) | NCLaw Jelly · PAC-NeRF observable state (mean) | Chamfer Distance: 17.491 -> 0.210 | Improved |
| fine-tune Plasticine pre-trained model with MASIV (ablation) | NCLaw Plasticine · PAC-NeRF observable state (mean) | Chamfer Distance: 6.535 -> 1.040 | Improved |
| fine-tune Sand pre-trained model with MASIV (ablation) | NCLaw Sand · PAC-NeRF observable state (mean) | Chamfer Distance: 14.396 -> 9.151 | Improved |
| increase training sequences from 1 to 3 | MASIV · Multi-sequence dataset (mean) | Chamfer Distance: 29.24 -> 0.57 | Improved |
| increase training sequences from 1 to 3 | GIC · Multi-sequence dataset (mean) | Chamfer Distance: 0.94 -> 1.39 | Hurt |
| replace GIC with MASIV on Spring-Gaus Real | GIC · Spring-Gaus Real observable state (mean) | PSNR: 38.11 -> 41.12 | Improved |
| replace GIC with MASIV on Spring-Gaus Synthetic future state | GIC · Spring-Gaus Synthetic future state (mean) | Chamfer Distance: 0.95 -> 1.20 | Hurt |
| replace GIC with MASIV on Spring-Gaus Synthetic observable state | GIC · Spring-Gaus Synthetic observable state (mean) | Chamfer Distance: 0.17 -> 0.13 | 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.
- NeuMA — NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics (NeurIPS 2024) · better on 5 of 5 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
- Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization (CVPR 2024 · similarity 0.87)
- Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation (CVPR 2025 · similarity 0.86)
- OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation (ICLR 2025 · similarity 0.86)
- UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation (CVPR 2025 · similarity 0.85)
- DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering (NeurIPS 2024 · similarity 0.85)
- NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics (NeurIPS 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.
