Yesnt:扩散重照明模型是否准备好用于捕获阶段合成？一种混合方法用于弥合差距
Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap
AI总结：
本文提出一种混合重照明框架，结合扩散先验与物理约束，实现更稳定的视频重照明效果。
摘要：
体积视频重照明对于将捕获的表演带入虚拟世界至关重要，但当前方法在交付时间稳定且可生产的结果方面存在困难。基于扩散的内在分解方法在单帧上显示出前景，但扩展到序列时却面临随机噪声和不稳定的问题，而视频扩散模型仍受内存和规模的限制。我们提出了一种混合重照明框架，结合了基于扩散的材料先验、时间正则化和物理驱动的渲染。我们的方法将多个随机估计的每帧材料属性聚集到时间一致的光照组件中，使用光流引导的正则化。对于间接效果，如阴影和反射，我们从高斯不透明场中提取网格代理，并在标准图形管线中进行渲染。在真实和合成捕获上的实验表明，这种混合策略在序列中实现了比仅扩散基线更稳定的重照明，同时扩展到视频扩散可行的剪辑长度之外。这些结果表明，混合方法，即在学习先验和物理约束之间取得平衡，是朝着可生产的体积视频重照明迈进的实用步骤。
英文摘要：
Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show promise for single frames, yet suffer from stochastic noise and instability when extended to sequences, while video diffusion models remain constrained by memory and scale. We propose a hybrid relighting framework that combines diffusion-derived material priors with temporal regularization and physically motivated rendering. Our method aggregates multiple stochastic estimates of per-frame material properties into temporally consistent shading components, using optical-flow-guided regularization. For indirect effects such as shadows and reflections, we extract a mesh proxy from Gaussian Opacity Fields and render it within a standard graphics pipeline. Experiments on real and synthetic captures show that this hybrid strategy achieves substantially more stable relighting across sequences than diffusion-only baselines, while scaling beyond the clip lengths feasible for video diffusion. These results indicate that hybrid approaches, which balance learned priors with physically grounded constraints, are a practical step toward production-ready volumetric video relighting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
