Research map / Point clouds / Shape and surface completion
Out-of-Core Surface Reconstruction via Global TGV Minimization
Nikolai Poliarnyi
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 out-of-core GPU TGV minimization instead of in-core GDMR | Ours vs GDMR · Citywall | peak RAM: 75 GB -> 13.17 GB | Improved |
| use out-of-core GPU TGV minimization instead of in-core GDMR | Ours vs GDMR · Citywall | processing time: 19 h -> 63 min | Improved |
| use out-of-core GPU TGV minimization instead of in-core GDMR | Ours vs GDMR · Breisach | peak RAM: 64 GB -> 10.07 GB | Improved |
| use out-of-core GPU TGV minimization instead of in-core GDMR | Ours vs GDMR · Breisach | processing time: 76 h -> 260 min | Improved |
| use GPU-accelerated out-of-core method instead of out-of-core SSR | Ours vs SSR 128K · Citywall | processing time: 58 h -> 63 min | Improved |
| use GPU-accelerated out-of-core method instead of out-of-core SSR | Ours vs SSR 128K · Citywall | peak RAM: 32*8.9 GB -> 13.17 GB | Improved |
| compare reconstruction quality with in-core GDMR on same depth maps | Ours vs GDMR · Citywall and Breisach | visual quality | No clear effect |
| use delta=6 r and eta=18 r near-surface widths (smaller or larger values) (ablation) | Ours · scale-diverse scenes | surface quality | Mixed |
Closest papers by meaning
- GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction (NeurIPS 2025 · similarity 0.85)
- FatesGS: Fast and Accurate Sparse-View Surface Reconstruction Using Gaussian Splatting with Depth-Feature Consistency (AAAI 2025 · similarity 0.85)
- D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction (NeurIPS 2025 · similarity 0.85)
- GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting (ICLR 2025 · similarity 0.85)
- GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields (NeurIPS 2024 · similarity 0.84)
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · 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.
