Research map / 3D vision / Gaussian splatting
D-Prism: Differentiable Primitives for Structured Dynamic Modeling
Xingyuan Yu, Yijin Li, Chong Zeng, Yuhang Ming, Hujun Bao, Guofeng Zhang
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 deformation network for primitive motion (ablation) | D-Prism · Dynamic Primitive Dataset (Rubik's Cube) | EPE: 0.177 -> 0.063 | Improved |
| add deformation network for primitive motion (ablation) | D-Prism · Dynamic Primitive Dataset (Rubik's Cube) | CD_d: 3.642 -> 3.237 | Improved |
| add deformation network for primitive motion (ablation) | D-Prism · Dynamic Primitive Dataset (Rubik's Cube) | EMD_d: 0.168 -> 0.114 | Improved |
| add clone operation (ablation) | D-Prism · D-NeRF (Jumpingjacks) | PSNR: 25.873 -> 29.069 | Improved |
| add clone operation (ablation) | D-Prism · D-NeRF (Mutant) | PSNR: 24.667 -> 26.518 | Improved |
| add clone operation (ablation) | D-Prism · D-NeRF (Jumpingjacks) | LPIPS: 0.058 -> 0.034 | Improved |
| add clone operation (ablation) | D-Prism · D-NeRF (Mutant) | SSIM: 0.934 -> 0.945 | Improved |
| lower merge threshold tau_o (more aggressive merging) vs default 0.7 (ablation) | D-Prism · Rubik's Cube and humanoid (qualitative) | primitive set quality | Hurt |
| raise merge threshold tau_o to 1 (merge only fully overlapped) (ablation) | D-Prism · Rubik's Cube and humanoid (qualitative) | primitive redundancy | Hurt |
| use D-Prism instead of DG-Mesh for motion tracking | D-Prism vs DG-Mesh · Dynamic Primitive Dataset (Rubik's Cube) | EPE: 0.181 -> 0.063 | Improved |
| use D-Prism instead of DG-Mesh for rendering | D-Prism vs DG-Mesh · D-NeRF (Jumpingjacks) | PSNR: 31.769 -> 29.069 | Hurt |
| use D-Prism instead of DG-Mesh for motion tracking | D-Prism vs DG-Mesh · Dynamic Primitive Dataset (Pliers) | EPE: 0.010 -> 0.014 | Mixed |
Closest papers by meaning
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.85)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.85)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.85)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.85)
- PRISM: Programming Interactive Scenes from Monocular Images for Embodied Simulation (NeurIPS 2026 · similarity 0.85)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.84)
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.
