发表机构
Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对非结构化视角采样下大规模高斯溅射的视角稀缺与生成方法缺陷，提出InceptionGS，通过平衡重建与生成、引入自适应先验修复问题区域，在真实场景实验中表现优异。
AI 中文摘要
实现真正沉浸式的大规模场景数字化，需要在所有可能的视角下实现一致且视觉美观的渲染。然而，由于场景复杂性、采集成本、疏忽或可访问性限制，收集覆盖大规模场景所有细节的多视角图像是不现实的。因此，采样视角往往高度非结构化——大部分场景得到了充分覆盖，但某些区域不可避免地缺乏足够观测。现有基于重建的方法易受视角稀缺影响，而基于生成的方法则存在泛化性、可控性和3D一致性问题。为应对这一挑战，我们提出InceptionGS，通过巧妙平衡重建与生成来实现高斯溅射的自举。从初始高斯溅射开始，InceptionGS通过软引入场景与视角自适应的生成先验，合理重新思考并修复视角稀缺导致的问题区域，同时保留其他区域的质量。在真实世界大规模场景上的大量实验表明，我们的方法在处理非结构化图像和提升高保真高斯溅射方面具有优越性和广泛适用性。更多视觉演示请参考补充视频。
英文摘要
Achieving truly immersive large-scale scene digitization necessitates consistent and visually pleasing rendering across all possible viewing perspectives. However, collecting multi-view images covering every fine detail of a large-scale scene is prohibitive due to scene complexity, capture cost, negligence, or accessibility constraints. As a result, the sampled views tend to be highly unstructured -- the majority of the scene is well covered yet certain regions inevitably lack sufficient observations. Existing reconstruction based methods are vulnerable to view scarcity while generation based approaches suffer from generalization, controllability, and 3D consistency issues. To address this challenge, we propose InceptionGS, which bootstraps Gaussian splatting by subtly balancing reconstruction and generation. Starting from an initial Gaussian splatting, InceptionGS reasonably rethinks and repairs problematic regions caused by view scarcity while preserving the quality elsewhere, by softly incorporating scene- and view-adaptive generative priors. Extensive experiments on real-world large-scale scenes demonstrate the superiority and broad applicability of our approach in handling unstructured imagery and boosting high-fidelity Gaussian splatting. Please refer to the supplementary video for better visual demonstrations.
