Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirectangular projection (ERP) can reduce capture effort via their full $360^{\circ}$ field of view, yet the resulting omnipresent visibility invalidates existing partitioning strategies that rely on local camera frustums, causing block-wise optimization to degenerate into global training. Thus, we propose PanoLOG, a two-stage coarse-to-fine framework equipped with a Geometry and Gradient-based Partitioning Strategy tailored for large-scale panoramic
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorWeijian Chen →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorWeibo Yao →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorYuhang Zhang →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorXiaolin Tang →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorGuo Wang →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorWeijun Zhang →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorXitong Gao →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorYihao Chen →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorHongde Qin →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
- Linked via arxiv authorLu Qi →
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction