Research map / Point clouds / Point cloud classification
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion
Junru Lin, Chirag Vashist, Mikaela Angelina Uy, Colton Stearns, Xuan Luo, Leonidas Guibas, Ke Li
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 DINO input to the motion network (ablation) | GMC · Synthetic global-motion scenes | SI-FID: 203.38 -> 188.98 | Improved |
| add DINO input to the motion network (ablation) | GMC · Synthetic global-motion scenes | SI-MPED: 50.35 -> 26.05 | Improved |
| add position input to the motion network (ablation) | GMC · Synthetic global-motion scenes | SI-FID: 198.72 -> 188.98 | Improved |
| add position input to the motion network (ablation) | GMC · Synthetic global-motion scenes | SI-MPED: 54.29 -> 26.05 | Improved |
| add local isometry loss (ablation) | GMC · Synthetic global-motion scenes | SI-FID: 252.09 -> 188.98 | Improved |
| add local isometry loss (ablation) | GMC · Synthetic global-motion scenes | SI-MPED: 69.38 -> 26.05 | Improved |
| add joint refinement stage (ablation) | GMC · Synthetic global-motion scenes | SI-FID: 194.42 -> 188.98 | Improved |
| add joint refinement stage (ablation) | GMC · Synthetic global-motion scenes | SI-MPED: 28.08 -> 26.05 | Improved |
| use GMC instead of PAPR in Motion on large global motion | GMC · Synthetic global-motion scenes | SI-MPED: 114.45 -> 16.47 | Improved |
| use GMC instead of PAPR in Motion on small local motion | GMC · Synthetic local-motion scenes | SI-FID: 117.94 -> 112.62 | No clear effect |
| use GMC on real-world global motion vs PAPR in Motion | GMC · Real-world global-motion scenes | SI-EMD: 944.33 -> 70.85 | Improved |
| use GMC to refine sparse-view 3DGS (end state 10 views) | GMC · Sparse+dense view NVS | PSNR: 28.71 -> 33.07 | 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.
- PAPR in Motion — PAPR in Motion: Seamless Point-level 3D Scene Interpolation (CVPR 2024) · better on 9 of 9 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
- MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025 · similarity 0.86)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · similarity 0.86)
- DeMo: Deep Motion Field Consensus with Learnable Kernels for Two-view Correspondence Learning (AAAI 2025 · similarity 0.86)
- PAPR in Motion: Seamless Point-level 3D Scene Interpolation (CVPR 2024 · similarity 0.86)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.86)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.85)
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.
