物理启发的用于 HDR 新视角合成的高斯泼溅
Physically Inspired Gaussian Splatting for HDR Novel View Synthesis
将本征反射率与可调环境光照解耦建模，并引入跨分支 HDR 一致性损失与光照引导的梯度缩放策略，为基于高斯泼溅的 HDR 新视角合成提供了显式监督和梯度均衡手段，可直接迁移到其他需要多曝光融合的神经渲染框架。
原文依据 PhysHDR-GS employs a complementary image-exposure (IE) branch and Gaussian-illumination (GI) branch
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高动态范围新视角合成（HDR-NVS）通过融合多曝光低动态范围（LDR）视图来重建具有动态细节的场景，但难以捕捉依赖环境光照的外观。通过约束色调映射结果来隐式监督 HDR 内容，无法纠正异常的 HDR 值，并导致欠曝/过曝区域中高斯点的梯度受限。为此，我们提出 PhysHDR-GS，一个物理启发的 HDR-NVS 框架，通过本征反射率和可调环境光照来建模场景外观。PhysHDR-GS 采用互补的图像-曝光（IE）分支和高斯-光照（GI）分支，分别忠实再现标准相机观测和捕捉依赖光照的外观变化。在训练过程中，所提出的跨分支 HDR 一致性损失为 HDR 内容提供显式监督，而光照引导的梯度缩放策略缓解了曝光偏置的梯度饥饿并减少了欠致密化的表示。在真实和合成数据集上的实验结果表明，我们在重建 HDR 细节方面具有优越性（例如，相比 HDR-GS 峰值信噪比提升 2.04 dB），同时保持实时渲染速度（高达 76 FPS）。代码和模型可在 https://huimin-zeng.github.io/PhysHDR-GS/ 获取。
英文原文摘要 1355 字符
High dynamic range novel view synthesis (HDR-NVS) reconstructs scenes with dynamic details by fusing multi-exposure low dynamic range (LDR) views, yet it struggles to capture ambient illumination-dependent appearance. Implicitly supervising HDR content by constraining tone-mapped results fails in correcting abnormal HDR values, and results in limited gradients for Gaussians in under/over-exposed regions. To this end, we introduce PhysHDR-GS, a physically inspired HDR-NVS framework that models scene appearance via intrinsic reflectance and adjustable ambient illumination. PhysHDR-GS employs a complementary image-exposure (IE) branch and Gaussian-illumination (GI) branch to faithfully reproduce standard camera observations and capture illumination-dependent appearance changes, respectively. During training, the proposed cross-branch HDR consistency loss provides explicit supervision for HDR content, while an illumination-guided gradient scaling strategy mitigates exposure-biased gradient starvation and reduces under-densified representations. Experimental results across realistic and synthetic datasets demonstrate our superiority in reconstructing HDR details (e.g., a PSNR gain of 2.04 dB over HDR-GS), while maintaining real-time rendering speed (up to 76 FPS). Code and models are available at https://huimin-zeng.github.io/PhysHDR-GS/.