用对数空间训练神经辐射场，让图像渲染更清晰、低光下表现更好。
Log NeRF: Comparing Spaces for Learning Radiance Fields
- 在对数RGB空间中训练NeRF，使外观表示更紧凑有效。
- 相同输入下，对数空间渲染质量更高，低光场景提升显著。
- 适用于需要高鲁棒性与低光表现的三维重建任务。
神经辐射场（NeRF）在新视角合成中表现优异，通常以sRGB图像为监督信号。然而，网络学习辐射场表示时所处的颜色空间未受足够重视。受双光照双色反射模型（BIDR）启发，该研究假设对数变换可简化光照与反照率的分离，从而促进更高效、紧凑的场景外观建模。为此，研究团队使用GoPro相机拍摄了约30段视频，并通过逆编码确保线性数据恢复。在不同颜色空间（线性、sRGB、GPLog、log RGB）下训练NeRF模型，将各网络输出统一转换至同一颜色空间后进行渲染与损失计算，实现不同空间下的表示学习对比。定量与定性评估表明，log RGB空间显著提升渲染质量，跨场景鲁棒性更强，尤其在低光条件下表现突出，且使用相同位深输入图像。进一步分析不同网络规模与NeRF变体验证了对数空间优势的普适性与稳定性。
原文摘要 · Abstract (English)
Neural Radiance Fields (NeRF) have achieved remarkable results in novel view synthesis, typically using sRGB images for supervision. However, little attention has been paid to the color space in which the network is learning the radiance field representation. Inspired by the BiIlluminant Dichromatic Reflection (BIDR) model, which suggests that a logarithmic transformation simplifies the separation of illumination and reflectance, we hypothesize that log RGB space enables NeRF to learn a more compact and effective representation of scene appearance. To test this, we captured approximately 30 videos using a GoPro camera, ensuring linear data recovery through inverse encoding. We trained NeRF models under various color space interpretations linear, sRGB, GPLog, and log RGB by converting each network output to a common color space before rendering and loss computation, enforcing representation learning in different color spaces. Quantitative and qualitative evaluations demonstrate that using a log RGB color space consistently improves rendering quality, exhibits greater robustness across scenes, and performs particularly well in low light conditions while using the same bit-depth input images. Further analysis across different network sizes and NeRF variants confirms the generalization and stability of the log space advantage.
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。