通过自适应分块优化，实现大场景高效高质新视角合成。
BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting
- 按内容复杂度自适应分块，均衡计算负载
- 引入辅助点解决独立优化监督不一致问题，提升重建质量
- 伪视图几何约束缓解拼接时空洞漂浮，适合单卡大场景重建
3D高斯泼溅（3DGS）在新视角合成任务中展现出巨大潜力。尽管分治范式已实现大场景重建，但场景分割、优化与合并过程仍面临挑战。本文提出BlockGaussian框架，结合内容感知的场景分割策略和可见性感知的分块优化方法，实现高效高质的大场景重建。具体而言，该方法考虑不同区域的内容复杂度差异，在分割阶段平衡计算负载，提升重建效率；为解决独立分块优化中的监督不匹配问题，引入辅助点以对齐真实监督信号，增强重建质量；此外，提出伪视图几何约束，有效缓解分块合并时因空中漂浮物导致的渲染退化。大量实验表明，该方法在多个基准上实现最佳性能：优化速度提升5倍，平均PSNR提高1.21 dB。尤为关键的是，其显著降低计算需求，可在单张24GB显存设备上完成大场景重建。
原文摘要 · Abstract (English)
The recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated remarkable potential in novel view synthesis tasks. The divide-and-conquer paradigm has enabled large-scale scene reconstruction, but significant challenges remain in scene partitioning, optimization, and merging processes. This paper introduces BlockGaussian, a novel framework incorporating a content-aware scene partition strategy and visibility-aware block optimization to achieve efficient and high-quality large-scale scene reconstruction. Specifically, our approach considers the content-complexity variation across different regions and balances computational load during scene partitioning, enabling efficient scene reconstruction. To tackle the supervision mismatch issue during independent block optimization, we introduce auxiliary points during individual block optimization to align the ground-truth supervision, which enhances the reconstruction quality. Furthermore, we propose a pseudo-view geometry constraint that effectively mitigates rendering degradation caused by airspace floaters during block merging. Extensive experiments on large-scale scenes demonstrate that our approach achieves state-of-the-art performance in both reconstruction efficiency and rendering quality, with a 5x speedup in optimization and an average PSNR improvement of 1.21 dB on multiple benchmarks. Notably, BlockGaussian significantly reduces computational requirements, enabling large-scale scene reconstruction on a single 24GB VRAM device. The project page is available at https://github.com/SunshineWYC/BlockGaussian
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。