用3D高斯点云统一处理2D/3D局部色调映射，提升HDR图像重建质量。
GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping
- 设计残差局部色调映射器，同时支持3D与2D空间的局部映射。
- 在损失层融合双路低动态范围渲染结果，提升真实感表现。
- 引入不确定性学习实现自适应权重调节，适合复杂场景重建。
高动态范围（HDR）新视角合成旨在利用多视角低动态范围（LDR）图像（不同曝光水平下拍摄）重建HDR场景。现有方法采用3D色调映射常导致重建不稳定，而使用2D色调映射则削弱了模型拟合LDR图像的能力。此外，全局色调映射器会阻碍HDR与LDR表示的学习。为此，我们提出GaussHDR，通过3D高斯点云统一3D与2D局部色调映射。具体地，设计一个接受额外上下文特征输入的残差局部色调映射器，用于3D和2D空间；在损失层面融合来自3D与2D局部色调映射的双重LDR渲染结果；针对不同场景中双结果平衡差异，引入不确定性学习并用于自适应调制。大量实验表明，GaussHDR在合成与真实场景中均显著优于现有最优方法。
原文摘要 · Abstract (English)
High dynamic range (HDR) novel view synthesis (NVS) aims to reconstruct HDR scenes by leveraging multi-view low dynamic range (LDR) images captured at different exposure levels. Current training paradigms with 3D tone mapping often result in unstable HDR reconstruction, while training with 2D tone mapping reduces the model's capacity to fit LDR images. Additionally, the global tone mapper used in existing methods can impede the learning of both HDR and LDR representations. To address these challenges, we present GaussHDR, which unifies 3D and 2D local tone mapping through 3D Gaussian splatting. Specifically, we design a residual local tone mapper for both 3D and 2D tone mapping that accepts an additional context feature as input. We then propose combining the dual LDR rendering results from both 3D and 2D local tone mapping at the loss level. Finally, recognizing that different scenes may exhibit varying balances between the dual results, we introduce uncertainty learning and use the uncertainties for adaptive modulation. Extensive experiments demonstrate that GaussHDR significantly outperforms state-of-the-art methods in both synthetic and real-world scenarios.
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。