论文标题
4K-NERF：超高分辨率的高富达神经辐射场
4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions
论文作者
论文摘要
在本文中，我们提出了一个名为4K-NERF的新颖有效的框架，以基于神经辐射场（NERF）的方法来追求超高分辨率的挑战性情况。基于NERF的方法的渲染过程通常取决于像素的方式，在像素方面，射线（或像素）在训练和推理阶段都独立处理，从而限制了其描述微妙细节的代表性能力，尤其是在提升到极高的分辨率时。我们通过探索射线相关性来解决该问题，以增强高频细节恢复。特别是，我们使用3D感知的编码器在较低的分辨率空间中有效地对几何信息进行建模，并通过3D感知的解码器恢复细节，以射线特征和编码器估计的深度为条件。基于斑块的采样的联合培训进一步促进了我们的方法，结合了以超过像素损失的感知正规化的监督。与现代NERF方法相比，我们的方法受益于使用几何感知的本地环境，可以显着提高高频细节的质量，并在4K超高分辨率的场景上实现最先进的视觉质量。 \ url {https://github.com/frozoul/4k-nerf}可用代码
In this paper, we present a novel and effective framework, named 4K-NeRF, to pursue high fidelity view synthesis on the challenging scenarios of ultra high resolutions, building on the methodology of neural radiance fields (NeRF). The rendering procedure of NeRF-based methods typically relies on a pixel-wise manner in which rays (or pixels) are treated independently on both training and inference phases, limiting its representational ability on describing subtle details, especially when lifting to a extremely high resolution. We address the issue by exploring ray correlation to enhance high-frequency details recovery. Particularly, we use the 3D-aware encoder to model geometric information effectively in a lower resolution space and recover fine details through the 3D-aware decoder, conditioned on ray features and depths estimated by the encoder. Joint training with patch-based sampling further facilitates our method incorporating the supervision from perception oriented regularization beyond pixel-wise loss. Benefiting from the use of geometry-aware local context, our method can significantly boost rendering quality on high-frequency details compared with modern NeRF methods, and achieve the state-of-the-art visual quality on 4K ultra-high-resolution scenarios. Code Available at \url{https://github.com/frozoul/4K-NeRF}
