Summary
PanoLOG is a two-stage coarse-to-fine framework for large-scale outdoor 3D Gaussian Splatting (3DGS) reconstruction from panoramic images. Scaling 3DGS to big outdoor scenes is costly in data acquisition and computation; equirectangular projection (ERP) panoramas reduce capture effort with a full 360-degree field of view, but their omnipresent visibility breaks existing partitioning strategies that rely on local camera frustums, causing block-wise optimization to degenerate into global training. PanoLOG addresses this with a Geometry and Gradient-based Partitioning Strategy (G2PS). In the global coarse stage, it uses sky-sphere modeling and panoramic monocular depth supervision for reliable geometry; in the refinement stage, G2PS constructs adaptive boundary volumes via disparity-driven uncertainty and assigns cameras using gradient-based importance scoring. The authors also introduce Pano360, the first large-scale panoramic dataset benchmark for outdoor scene reconstruction. Experiments show G2PS achieves state-of-the-art rendering quality while preserving scalable block-parallel training. Models, training code, and the dataset are publicly released (arXiv:2607.08769).
论文概要
研究领域: CV
作者: Weijian Chen, Weibo Yao, Yuhang Zhang, Xiaolin Tang, Guo Wang, Weijun Zhang, Xitong Gao, Yihao Chen, Hongde Qin, Lu Qi
发布时间: 2026-07-09
arXiv: 2607.08769
English Translation
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 (G²PS) tailored for large-scale panoramic 3DGS reconstruction.
- Global coarse stage: PanoLOG leverages sky-sphere modeling and panoramic monocular depth supervision for reliable geometry.
- Refinement stage: G²PS builds adaptive boundary volumes via disparity-driven uncertainty and assigns cameras through gradient-based importance scoring.
The authors also construct
Pano360, the first large-scale panoramic dataset benchmark for outdoor scene reconstruction. Extensive experiments show that G²PS achieves state-of-the-art rendering quality while maintaining scalable block-parallel training. Models, training code, and the dataset are all publicly released.
---
*Auto-collected on 2026-07-12. Original Chinese summary preserved above; translation covers the abstract as provided.*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178379388