Research map / 3D vision / 3D generation
XDen-1K: A Density Field Dataset of Real-World Objects
Jingxuan Zhang, Tianqi Yu, Yatu Zhang, Jinze Wu, Kaixin Yao, Jingyang Liu, Yuyao Zhang, Jiayuan Gu, Jingyi Yu
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 biplanar X-ray conditioning (X-Field) to PartField (ablation) | PartField · Volumetric segmentation (synthetic) | IoU: 53.185 -> 72.645 | Improved |
| add biplanar X-ray conditioning (X-Field) to PartField (ablation) | PartField · Volumetric segmentation (real) | IoU: 38.410 -> 49.251 | Improved |
| use manual part labels instead of X-Field predicted segmentation prior (ablation) | reconstruction pipeline · Reprojection error on real X-rays (LAT) | mean error: 1.121 -> 0.778 | Improved |
| use manual part labels instead of X-Field predicted segmentation prior (ablation) | reconstruction pipeline · Reprojection error on real X-rays (PA) | mean error: 0.724 -> 0.498 | Improved |
| add manually modeled interior structure priors (ablation) | reconstruction pipeline · XDen-1K reconstruction | accuracy | Improved |
| add NeRF2Physics CoM guidance to AnyGrasp | AnyGrasp · CoM-guided grasping | success rate (%): 27.50 -> 55.00 | Improved |
| add CoM from XDen-1K reconstruction to AnyGrasp | AnyGrasp · CoM-guided grasping | success rate (%): 27.50 -> 77.75 | Improved |
| add CoM from XDen-1K reconstruction to AnyGrasp | AnyGrasp · CoM-guided grasping | Joint-7 torque (N m): 0.521 -> 0.435 | Improved |
| add CoM from XDen-1K reconstruction to AnyGrasp | AnyGrasp · CoM-guided grasping | mean torque (N m): 9.645 -> 9.497 | 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.
- PartField — PartField: Learning 3D Feature Fields for Part Segmentation and Beyond (ICCV 2025) · better on 2 of 2 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
- PhysGS: Bayesian-Inferred Gaussian Splatting for Physical Property Estimation (CVPR 2026 · similarity 0.86)
- Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image (NeurIPS 2026 · similarity 0.84)
- PhysX-3D: Physical-Grounded 3D Asset Generation (NeurIPS 2025 · similarity 0.84)
- Physical Property Understanding from Language-Embedded Feature Fields (CVPR 2024 · similarity 0.84)
- Geometry-Centered 3D Latent World Models for Growing Surfaces (NeurIPS 2026 · similarity 0.84)
- HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video (NeurIPS 2025 · similarity 0.83)
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.
