HOIGS: Human-Object Interaction Gaussian Splatting
About
Reconstructing dynamic scenes with complex human-object interactions is a fundamental challenge in computer vision and graphics. Existing Gaussian Splatting methods either rely on human pose priors while neglecting dynamic objects, or approximate all motions within a single field, limiting their ability to capture interaction-rich dynamics. To address this gap, we propose Human-Object Interaction Gaussian Splatting (HOIGS), which explicitly models interaction-induced deformation between humans and objects through a cross-attention-based HOI module. Distinct deformation baselines are employed to extract features: HexPlane for humans and Cubic Hermite Spline (CHS) for objects. By integrating these heterogeneous features, HOIGS effectively captures interdependent motions and improves deformation estimation in scenarios involving occlusion, contact, and object manipulation. Comprehensive experiments on multiple datasets demonstrate that our method consistently outperforms state-of-the-art human-centric and 4D Gaussian approaches, highlighting the importance of explicitly modeling human-object interactions for high-fidelity reconstruction.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Monocular dynamic scene reconstruction | HOSNeRF (test) | Backpack PSNR25.78 | 12 | |
| Human-Object Interaction Reconstruction | ARCTIC 9 (per-scene) | Capsulemachine PSNR27.05 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Backpack_1 | PSNR31.79 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Plasticcontainer_1 | PSNR33.1 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Plasticcontainer_2 | PSNR32.39 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Suitcase_2 | PSNR34.58 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Backpack_3 | PSNR30.17 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Plasticcontainer_3 | PSNR29.38 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Backpack_6 | PSNR29.05 | 4 | |
| Monocular dynamic scene reconstruction | BEHAVE Trashbin_6 | PSNR31.62 | 4 |