发表机构
Hefei University of Technology; The Hong Kong University of Science and Technology, Guangzhou; The University of Tokyo（合肥工业大学; 香港科技大学（广州）; 东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FujinSplat在RAW域中分离烟雾介质与ISP变换，通过基础ISP和场景无关控制器修正视图，训练静态3D高斯表示，在RealX3D基准上显著超越现有方法。
AI 中文摘要
烟雾场景的外观由相机同时记录的两个过程共同塑造：参与介质以视点相关的方式改变场景辐射度，随后图像信号处理器（ISP）通过非线性色调和颜色变换重新映射结果。恢复干净的3D场景需要将两者分离。逐视图的sRGB去雾仅在ISP将两者纠缠之后进行；标准3D重建忽略介质并将其吸收进场景几何和辐射度中。FujinSplat在RAW域中解决该问题，在该域中两个过程仍可分离。一个逐场景的基础ISP从场景的有雾RAW捕获中拟合到其自身的相机渲染，然后冻结，提供不执行去雾的固定光度锚点。分析专家修正揭示了一个紧凑的低维修正空间，可仅从RAW中识别。因此，FujinSplat在训练姿态处拟合逐视图动作答案，并训练一个单一的场景无关控制器从RAW回归它们；修正后的视图监督一个静态3D高斯表示，并联合一个有界的逐视图残差以调和跨视图光度不一致性。在RealX3D真实世界烟雾基准上，FujinSplat明显优于最强可比基线，领先于基于物理的重建和先恢复后3DGS的流程。
英文摘要
The appearance of a smoky scene is shaped by two processes that a camera records together: the participating medium alters scene radiance in a view-dependent way, and the image signal processor (ISP) then remaps the result through a nonlinear tone and color transformation. Recovering a clean 3D scene requires separating both. Per-view sRGB dehazing acts only after the ISP has entangled them; standard 3D reconstruction ignores the medium and absorbs it into scene geometry and radiance. FujinSplat addresses the problem in the RAW domain, where the two processes remain separable. A per-scene Base ISP is fitted from the scene's hazy RAW captures to its own camera renderings and then frozen, providing a fixed photometric anchor that performs no dehazing. Analyzing expert corrections reveals a compact, low-dimensional correction space identifiable from RAW alone. FujinSplat therefore fits per-view action answers at the training poses and trains a single scene-agnostic controller to regress them from RAW; the corrected views supervise one static 3D Gaussian representation, jointly with a bounded per-view residual that reconciles cross-view photometric inconsistencies. On the RealX3D real-world smoke benchmark FujinSplat clearly outperforms the strongest comparable baseline, ahead of both physics-based reconstruction and restoration-then-3DGS pipelines. Code is available at https://github.com/I2WM/FujinSplat.
Comments20 pages, 11 figures, including supplementary material. Updated author affiliations and funding acknowledgments; scientific content unchanged. Code: https://github.com/I2WM/FujinSplat
