Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.02794 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908937732751360 |
|---|---|
| author | Kim, Mijeong Kim, Gunhee Choi, Jungyoon Roh, Wonjae Han, Bohyung |
| author_facet | Kim, Mijeong Kim, Gunhee Choi, Jungyoon Roh, Wonjae Han, Bohyung |
| contents | We introduce PhysGaia, a novel physics-aware benchmark for Dynamic Novel View Synthesis (DyNVS) that encompasses both structured objects and unstructured physical phenomena. While existing datasets primarily focus on photorealistic appearance, PhysGaia is specifically designed to support physics-consistent dynamic reconstruction. Our benchmark features complex scenarios with rich multi-body interactions, where objects realistically collide and exchange forces. Furthermore, it incorporates a diverse range of materials, including liquid, gas, textile, and rheological substance, moving beyond the rigid-body assumptions prevalent in prior work. To ensure physical fidelity, all scenes in PhysGaia are generated using material-specific physics solvers that strictly adhere to fundamental physical laws. We provide comprehensive ground-truth information, including 3D particle trajectories and physical parameters (e.g., viscosity), enabling the quantitative evaluation of physical modeling. To facilitate research adoption, we also provide integration pipelines for recent 4D Gaussian Splatting models along with our dataset and their results. By addressing the critical shortage of physics-aware benchmarks, PhysGaia can significantly advance research in dynamic view synthesis, physics-based scene understanding, and the integration of deep learning with physical simulation, ultimately enabling more faithful reconstruction and interpretation of complex dynamic scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02794 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis Kim, Mijeong Kim, Gunhee Choi, Jungyoon Roh, Wonjae Han, Bohyung Graphics Artificial Intelligence Computer Vision and Pattern Recognition We introduce PhysGaia, a novel physics-aware benchmark for Dynamic Novel View Synthesis (DyNVS) that encompasses both structured objects and unstructured physical phenomena. While existing datasets primarily focus on photorealistic appearance, PhysGaia is specifically designed to support physics-consistent dynamic reconstruction. Our benchmark features complex scenarios with rich multi-body interactions, where objects realistically collide and exchange forces. Furthermore, it incorporates a diverse range of materials, including liquid, gas, textile, and rheological substance, moving beyond the rigid-body assumptions prevalent in prior work. To ensure physical fidelity, all scenes in PhysGaia are generated using material-specific physics solvers that strictly adhere to fundamental physical laws. We provide comprehensive ground-truth information, including 3D particle trajectories and physical parameters (e.g., viscosity), enabling the quantitative evaluation of physical modeling. To facilitate research adoption, we also provide integration pipelines for recent 4D Gaussian Splatting models along with our dataset and their results. By addressing the critical shortage of physics-aware benchmarks, PhysGaia can significantly advance research in dynamic view synthesis, physics-based scene understanding, and the integration of deep learning with physical simulation, ultimately enabling more faithful reconstruction and interpretation of complex dynamic scenes. |
| title | PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis |
| topic | Graphics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.02794 |