Research map / 3D vision / 3D generation
SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge
Yumeng He, Ying Jiang, Jiayin Lu, Yin Yang, Chenfanfu Jiang
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 VLM-derived part-image guidance (ablation) | SPARK · GAPartNet test | F-Score@0.1: 0.3755 -> 0.4214 | Improved |
| add articulation-state data augmentation (ablation) | SPARK · GAPartNet test | F-Score@0.1: 0.3675 -> 0.4214 | Improved |
| add differentiable-FK joint optimization (ablation) | SPARK · GAPartNet test | AxisErr: 0.3148 -> 0.1577 | Improved |
| add differentiable-FK joint optimization (ablation) | SPARK · GAPartNet test | TypeErr: 0.2000 -> 0.0500 | Improved |
| add differentiable-FK joint optimization (ablation) | SPARK · GAPartNet test | PivotErr: 0.2388 -> 0.1653 | Improved |
| part-level guided DiT vs PartCrafter at loose threshold | SPARK · GAPartNet test | F-Score@0.5: 0.8840 -> 0.8959 | No clear effect |
| part-level guided DiT vs PartCrafter at strict threshold | SPARK · GAPartNet test | F-Score@0.1: 0.3600 -> 0.4151 | Improved |
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.
- PartCrafter — PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025) · better on 3 of 3 shared results
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
- URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets (NeurIPS 2026 · similarity 0.90)
- URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model (NeurIPS 2025 · similarity 0.89)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.88)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.88)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.87)
- General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process (NeurIPS 2024 · similarity 0.87)
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.
