Research map / 3D vision / Gaussian splatting
PD$^{2}$GS: Part-Level Decoupling and Continuous Deformation of Articulated Objects via Gaussian Splatting
Haowen Wang, Xiaoping Yuan, Zhao Jin, Zhen Zhao, Zhengping Che, Yousong Xue, Jing Tian, Yakun Huang, Jian Tang
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 coarse-to-fine refinement (visibility-guided SAM prompting and boundary-aware Gaussian splitting) (ablation) | PD2GS · Oven with multiple movable panels | part separation quality (qualitative) | Improved |
| use PD2GS instead of ArtGS for unseen-state rendering | PD2GS · Unseen-state rendering (Storage) | PSNR: 26.82 -> 28.02 | Improved |
| use PD2GS instead of ArtGS for unseen-state rendering | PD2GS · Unseen-state rendering (Storage) | LPIPS: 0.12 -> 0.09 | Improved |
| add more interaction states (two -> four states) (ablation) | PD2GS · PartNet-Mobility | CD-w: 6.38 -> 3.02 | Improved |
| use PD2GS instead of ArtGS on real objects | PD2GS · RS-Art | Axis Ang 0 error: 51.24 -> 1.46 | Improved |
| use PD2GS instead of ArtGS on two-part objects | PD2GS · PartNet-Mobility | Axis Ang 0 error: 2.37 -> 0.33 | Improved |
| add depth input (DTArt versus PD2GS RGB only) | DTArt · PartNet-Mobility | CD-w: 3.02 -> 2.18 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- D-NeRF — D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.91)
- ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos (CVPR 2025 · similarity 0.89)
- DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data (NeurIPS 2025 · similarity 0.89)
- TAGA: Self-supervised Learning for Template-free Animatable Gaussian Articulated Model (CVPR 2025 · similarity 0.88)
- REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints (NeurIPS 2025 · similarity 0.88)
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.
