Research map / 3D vision / Face and shape
Physical Simulation Layer for Accurate 3D Modeling
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use online differentiable simulation instead of surrogate-model offline simulation for optimization | DeepSDF shape optimization · Chair | CD: 1.40 -> 0.69 | Helped |
| Use online differentiable simulation instead of surrogate-model offline simulation for optimization | DeepSDF shape optimization · Chair | SR: 59.8% -> 62.8% | Helped |
| Use online differentiable simulation instead of surrogate-model offline simulation for optimization | DeepSDF shape optimization · Bench | SR: 52.4% -> 68.4% | Helped |
| Use online differentiable simulation instead of surrogate-model offline simulation for optimization | DeepSDF shape optimization · Table | CD: 6.40 -> 1.72 | Helped |
| Train the latent space with physical stability loss, adding it to DeepSDF | Phys-DeepSDF · Chair shape optimization | SR: 62.8% -> 71.8% | Helped |
| Train the latent space with physical stability loss, adding it to DeepSDF | Phys-DeepSDF · Bench shape optimization | CD: 1.21 -> 0.70 | Helped |
| Train the latent space with physical stability loss, adding it to DeepSDF | Phys-DeepSDF · Table shape optimization | SR: 55.6% -> 68.6% | Helped |
| Train with surrogate-model physics supervision | DeepSDF · Chair shape reconstruction | CD: 1.72 -> 1.94 | Hurt |
| Train with surrogate-model physics supervision | DeepSDF · Bench shape reconstruction | CD: 5.09 -> 5.97 | Hurt |
| Train with differentiable simulation stability loss | Phys-DeepSDF · Chair shape reconstruction | CD: 1.72 -> 1.68 | Helped |
| Train with differentiable simulation stability loss | Phys-DeepSDF · Bench shape reconstruction | CD: 5.09 -> 4.74 | Helped |
| Train with differentiable simulation stability loss | Phys-DeepSDF · Table shape reconstruction | CD: 2.54 -> 2.48 | Helped |
Closest papers by meaning
- Physically Compatible 3D Object Modeling from a Single Image (NeurIPS 2024 · similarity 0.87)
- PhysX-3D: Physical-Grounded 3D Asset Generation (NeurIPS 2025 · similarity 0.86)
- GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors (CVPR 2024 · similarity 0.85)
- Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image (NeurIPS 2026 · similarity 0.85)
- Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication (NeurIPS 2024 · similarity 0.85)
- PhyRecon: Physically Plausible Neural Scene Reconstruction (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.