融合物理模型与生成技术，实现城市场景高精度逆渲染与可控生成。
BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering
- 结合物理建模与生成先验，恢复一致且真实的场景属性。
- 在真实与合成场景中均优于基线方法，生成视频质量高。
- 支持新视角光照、夜间模拟及动态物体编辑，适合影视与自动驾驶应用。
从视频中逆向渲染城市场景可支持内容创作和自动驾驶仿真等应用。基于物理的渲染方法虽遵循光照物理规律，但易产生重建与渲染伪影；生成模型虽能生成逼真视频，却缺乏一致性与可控性。我们提出BRDFusion，一种统一框架，融合逆渲染与正向渲染的互补模型：物理模型显式恢复一致的场景属性，生成先验缓解优化歧义；正向渲染时，物理模型提供可控制的渲染输出，生成模型则去噪并修正伪影。因此，本方法在真实与合成场景中均生成高质量视频，并支持新视角光照调整、夜间模拟及动态物体插入/编辑。项目主页：https://shigon255.github.io/brdfusion-page/
原文摘要 · Abstract (English)
Inverse rendering of urban scenes from captured videos enables numerous applications, including content creation and autonomous driving simulation. Physically-based rendering methods follow and control lighting physics, but suffer from reconstruction and rendering artifacts. While generative models produce realistic videos, they offer limited consistency and controllability. We present BRDFusion, a unified framework that combines two complementary models for inverse and forward rendering. Specifically, BRDFusion recovers explicit, consistent scene properties with physical modeling and alleviates optimization ambiguity with generative priors. During forward rendering, the physical model provides controllable rendering from the scene configuration, and the generative model denoises and fixes artifacts. Therefore, our method produces high-quality videos while allowing precise control, outperforming baselines in real and synthetic scenes. Moreover, BRDFusion supports novel-view relighting, night simulation, and dynamic object insertion/editing. Project page: https://shigon255.github.io/brdfusion-page/
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。