Research map / 3D vision / Depth and stereo
Discrete Laplace Operator Estimation for Dynamic 3D Reconstruction
Xiangyu Xu, Enrique Dunn
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 |
|---|---|---|---|
| use DTW arc distance instead of Euclidean distance for sequencing (SR, nonlinear motion, initial structure) (ablation) | DLOE sequencing · Motion capture (nonlinear motion) | Kendall rank correlation: 0.9807 -> 0.9570 | Hurt |
| use DTW arc distance instead of Euclidean distance for sequencing (MDS, optimized structure, nonlinear motion) (ablation) | DLOE sequencing · Motion capture (nonlinear motion) | Kendall rank correlation: 0.7044 -> 1 | Improved |
| use DTW arc distance instead of Euclidean distance for sequencing (SR, initial structure, repeating motion) (ablation) | DLOE sequencing · Motion capture (repeating motion) | Kendall rank correlation: 0.6754 -> 0.9711 | Improved |
| use DTW arc distance instead of Euclidean distance for sequencing (SHP, optimized structure, repeating motion) (ablation) | DLOE sequencing · Motion capture (repeating motion) | Kendall rank correlation: 0.7912 -> 0.7934 | No clear effect |
| sequence from optimized structure instead of initial structure (SHP, Euclidean, nonlinear motion) (ablation) | DLOE sequencing · Motion capture (nonlinear motion) | Kendall rank correlation: 0.4368 -> 0.9996 | Improved |
| sequence from optimized structure instead of initial structure (MDS, Euclidean, nonlinear motion) (ablation) | DLOE sequencing · Motion capture (nonlinear motion) | Kendall rank correlation: 0.7614 -> 0.7044 | Hurt |
| sequence from optimized structure instead of initial structure (SHP, arc distance, repeating motion) (ablation) | DLOE sequencing · Motion capture (repeating motion) | Kendall rank correlation: 0.3947 -> 0.7934 | Improved |
| include all geometric terms (smoothness, locality, reconstructability) in the cost function (ablation) | DLOE · Motion capture, moderate-to-high 2D noise | reconstruction error | Improved |
| increase 2D observation noise from 1 to 5 pixels std | DLOE · Motion capture | 3D reconstruction error | Hurt |
| use DLOE without sequencing instead of SEDL at lower frame rates | DLOE · Motion capture (30, 15, 7.5 Hz) | 3D reconstruction error | Improved |
| use DLOE instead of SEDL and TB under 10-50% missing points | DLOE · Motion capture | 3D reconstruction error | Improved |
| drop 10-50% of frames (non-uniform density), DLOE vs other methods | DLOE · Motion capture | 3D reconstruction error | Improved |
Closest papers by meaning
- Kronecker-Markov Prior for Dynamic 3D Reconstruction (TPAMI 2016 · similarity 0.86)
- In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D Landmarks (CVPR 2020 · similarity 0.86)
- Parametric SDF for Dynamic Surface Reconstruction (ECCV 2026 · similarity 0.85)
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (TPAMI 2016 · similarity 0.85)
- Shape of Motion: 4D Reconstruction from a Single Video (ICCV 2025 · similarity 0.85)
- ReMatching Dynamic Reconstruction Flow (ICLR 2025 · 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.
