Research map / 3D vision / Gaussian splatting
Learning Implicit Constitutive Laws for Dynamic 3D Gaussian Splatting from Monocular Videos
Xiaoyang Liu, Kai Han
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 GCA (vs NeuMA) | NeuMA · Synthetic benchmark | average Chamfer Distance: 0.954 -> 0.496 | Improved |
| add rank-based depth anchors (RDGA) (ablation) | GCA · Synthetic (Elastomer Ball) | Chamfer Distance: 3.842 -> 0.922 | Improved |
| add global alignment term (ablation) | GCA · Synthetic benchmark | Chamfer Distance: >100 -> 0.922 | Improved |
| use rank-based loss instead of L1 depth loss (ablation) | GCA · Synthetic benchmark | average Chamfer Distance: 0.844 -> 0.496 | Improved |
| add anchor supervision (ablation) | GCA · Synthetic (Plasticine Cat) | Chamfer Distance: 0.510 -> 0.318 | Improved |
| add Constitutive Prior Regularizer (CPR) (ablation) | GCA · Synthetic (Elastomer Ball) | Chamfer Distance: 1.024 -> 0.922 | Improved |
| add CPR (ablation) | GCA · Synthetic (Gel Duck) | Chamfer Distance: 0.694 -> 0.702 | No clear effect |
| use LoRA instead of full fine-tuning (ablation) | GCA · Efficiency comparison | Chamfer Distance: 1.35 -> 0.50 | Improved |
| add monocular depth supervision to PAC-NeRF (ablation) | PAC-NeRF · Monocular setting (Ball, Cat) | Chamfer Distance: 0.85 -> >100 | Hurt |
| remove target law from CPR library (ablation) | GCA · Synthetic (Plasticine Cat) | Chamfer Distance: 0.318 -> 0.397 | Hurt |
| remove target law from CPR library (ablation) | GCA · Synthetic (Elastomer Ball) | Chamfer Distance: 0.922 -> 0.976 | Hurt |
| use GCA instead of NeuMA for law recovery | NeuMA · JellyDuck constitutive response | response error (%): 39.6 -> 8.0 | 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 12 of 12 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
- Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos (NeurIPS 2025 · similarity 0.89)
- MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene (NeurIPS 2025 · similarity 0.88)
- MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos (NeurIPS 2026 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.87)
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.
