通过跨环境拍摄提升高保真光照重建，解决材质与光照混淆难题。
ReCap: Better Gaussian Relighting with Cross-Environment Captures
- 联合优化多光照表示，共享同一组材质属性以减少混淆
- 在扩展基准上显著优于现有方法，实现更准确的光照重渲染
- 适合需要真实虚拟物体放置的3D渲染与数字孪生应用
在多样未知环境中实现精确的3D物体光照重渲染，对真实感虚拟物体放置至关重要。由于存在反照率-光照混淆问题，现有方法常无法生成忠实的光照效果。缺乏有效约束时，训练视图可由大量光照与材质组合解释，与实际用于重渲染的环境贴图无物理对应关系。本文提出ReCap，将跨环境捕获作为多任务目标，提供突破混淆的关键监督。ReCap联合优化多个共享相同材质属性的光照表示，自然在共同材质属性周围形成一致的光照表示，利用不同视角间共性与差异。这种一致性实现了物理合理的光照重建与鲁棒的材质估计，二者均是准确重渲染的核心。结合简化着色函数和有效后处理，ReCap在扩展的重渲染基准上超越所有领先方法。
原文摘要 · Abstract (English)
Accurate 3D objects relighting in diverse unseen environments is crucial for realistic virtual object placement. Due to the albedo-lighting ambiguity, existing methods often fall short in producing faithful relights. Without proper constraints, observed training views can be explained by numerous combinations of lighting and material attributes, lacking physical correspondence with the actual environment maps used for relighting. In this work, we present ReCap, treating cross-environment captures as multi-task target to provide the missing supervision that cuts through the entanglement. Specifically, ReCap jointly optimizes multiple lighting representations that share a common set of material attributes. This naturally harmonizes a coherent set of lighting representations around the mutual material attributes, exploiting commonalities and differences across varied object appearances. Such coherence enables physically sound lighting reconstruction and robust material estimation - both essential for accurate relighting. Together with a streamlined shading function and effective post-processing, ReCap outperforms all leading competitors on an expanded relighting benchmark.
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。