Name
Abstract | ||
|---|---|---|
Deep simulations have gained widespread attention owing to their excellent acceleration performances. However, these methods cannot provide effective collision detection and response strategies. We propose a deep interactive physical simulation framework that can effectively address tool-object collisions. The framework can predict the dynamic information by considering the collision state. In particular, the graph neural network is chosen as the base model, and a collision-aware recursive regression module is introduced to update the network parameters recursively using interpenetration distances calculated from the vertex-face and edge-edge tests. Additionally, a novel self-supervised collision term is introduced to provide a more compact collision response. This study extensively evaluates the proposed method and shows that it effectively reduces interpenetration artifacts while ensuring high simulation efficiency. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1186/s42492-022-00113-4 | Visual Computing for Industry, Biomedicine, and Art |
Keywords | DocType | Volume |
Deep physical simulation, Collision-aware, Continuous collision detection, Graph neural network | Journal | 5 |
Issue | ISSN | Citations |
1 | 2524-4442 | 0 |
PageRank | References | Authors |
0.34 | 5 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xin Zhu | 1 | 0 | 0.34 |
| Yinling Qian | 2 | 0 | 0.34 |
| Qiong Wang | 3 | 30 | 15.18 |
| Ziliang Feng | 4 | 0 | 1.01 |
| Pheng-Ann Heng | 5 | 3565 | 280.98 |