PPISP：辐射场重建中光度变化的物理合理补偿与控制
PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction
把相机 ISP 拆成物理可解释的模块并训练一个控制器为新视角预测 ISP 参数，可直接替换 NeRF/3DGS 中常用的逐帧 latent 或仿射颜色校正，解决多视角光度不一致且无需新视角真值即可公平评测。
原文依据 A dedicated PPISP controller, trained on the input views, predicts ISP parameters for novel viewpoints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多视角三维重建方法仍然对由相机光学特性和图像信号处理（ISP）变化引起的光度不一致高度敏感。现有的缓解策略，如逐帧潜变量或仿射颜色校正，缺乏物理依据，且对新视角的泛化能力较差。我们提出物理合理的 ISP（PPISP）校正模块，通过基于物理且可解释的变换，将相机固有效应与拍摄相关效应解耦。一个专用的 PPISP 控制器在输入视角上训练，为新视角预测 ISP 参数，类似于真实相机中的自动曝光和自动白平衡。这一设计使得在无法获取真值图像的情况下，也能对新视角进行真实且公平的评估。PPISP 在标准基准上取得了 SotA 性能，同时提供直观的控制，并支持在元数据可用时将其集成进来。源代码见：https://github.com/nv-tlabs/ppisp
英文原文摘要 1024 字符
Multi-view 3D reconstruction methods remain highly sensitive to photometric inconsistencies arising from camera optical characteristics and variations in image signal processing (ISP). Existing mitigation strategies such as per-frame latent variables or affine color corrections lack physical grounding and generalize poorly to novel views. We propose the Physically-Plausible ISP (PPISP) correction module, which disentangles camera-intrinsic and capture-dependent effects through physically based and interpretable transformations. A dedicated PPISP controller, trained on the input views, predicts ISP parameters for novel viewpoints, analogous to auto exposure and auto white balance in real cameras. This design enables realistic and fair evaluation on novel views without access to ground-truth images. PPISP achieves SotA performance on standard benchmarks, while providing intuitive control and supporting the integration of metadata when available. The source code is available at: https://github.com/nv-tlabs/ppisp