让3D场景渲染更真实，自动修复过曝欠曝问题
Physically Inspired Gaussian Splatting for HDR Novel View Synthesis
- 用物理光照模型分离反光与环境光，提升细节还原
- 相比现有方法，高光部分清晰度提升2.04 dB，实时渲染达76帧
- 适合做高质量影视/游戏渲染的开发者和研究者
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）图像重建包含动态细节的场景，但难以捕捉依赖环境光照的外观变化。现有方法通过约束色调映射结果隐式监督HDR内容，导致异常HDR值无法修正，且在过曝/欠曝区域中高斯点梯度受限。为此，本文提出物理启发的HDR-NVS框架PhysHDR-GS，通过内在反射率与可调环境光照建模场景外观。该框架包含互补的图像曝光（IE）分支和高斯光照（GI）分支，分别精准再现标准相机观测结果与光照依赖的外观变化。训练阶段，提出的跨分支HDR一致性损失对HDR内容提供显式监督，光照引导的梯度缩放策略缓解了曝光偏差导致的梯度饥饿，减少欠密集表示。在真实与合成数据集上的实验表明，本方法在重建HDR细节方面显著优于现有方法（如比HDR-GS提升2.04 dB PSNR），同时保持实时渲染速度（最高达76 FPS）。代码与模型已公开于https://huimin-zeng.github.io/PhysHDR-GS/。
原文摘要 · Abstract (English)
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/.
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。