NeRF

发布日期: 2025-11-25

更新日期: 2025-11-26

文章字数: 1.7k

阅读时长: 7 分

阅读次数:

⚠️ 以下所有内容总结都来自于大语言模型的能力，如有错误，仅供参考，谨慎使用
🔴 请注意：千万不要用于严肃的学术场景，只能用于论文阅读前的初筛！
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ，还请您给我们一些鼓励！⭐️ HuggingFace免费体验

2025-11-25 更新

NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior

Authors:Dongbo Shi, Shen Cao, Bojian Wu, Jinhui Guo, Lubin Fan, Renjie Chen, Ligang Liu, Jieping Ye

In this paper, we introduce NoPe-NeRF++, a novel local-to-global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose priors. Existing methods, particularly NoPe-NeRF, which focus solely on the local relationships within images, often struggle to recover accurate camera poses in complex scenarios. To overcome the challenges, our approach begins with a relative pose initialization with explicit feature matching, followed by a local joint optimization to enhance the pose estimation for training a more robust NeRF representation. This method significantly improves the quality of initial poses. Additionally, we introduce global optimization phase that incorporates geometric consistency constraints through bundle adjustment, which integrates feature trajectories to further refine poses and collectively boost the quality of NeRF. Notably, our method is the first work that seamlessly combines the local and global cues with NeRF, and outperforms state-of-the-art methods in both pose estimation accuracy and novel view synthesis. Extensive evaluations on benchmark datasets demonstrate our superior performance and robustness, even in challenging scenes, thus validating our design choices.

本文介绍了一种无需姿态先验训练神经网络辐射场（NeRF）的新型局部到全局优化算法NoPe-NeRF++。现有方法，尤其是仅关注图像内部局部关系的NoPe-NeRF，在复杂场景中往往难以恢复准确的相机姿态。为了克服这一挑战，我们的方法首先通过显式特征匹配进行相对姿态初始化，然后进行局部联合优化，以提高姿态估计，训练更稳健的NeRF表示。这种方法显著提高了初始姿态的质量。此外，我们引入了全局优化阶段，通过捆绑调整引入几何一致性约束，整合特征轨迹以进一步调整姿态，并共同提升NeRF的质量。值得注意的是，我们的方法是将局部和全局线索无缝结合到NeRF的第一项工作，在姿态估计准确性和新型视图合成方面都优于最新技术方法。在基准数据集上的广泛评估证明了我们设计的优越性及稳健性，即使在具有挑战性的场景中也是如此。

论文及项目相关链接

PDF

Summary
NeRF训练中的局部到全局优化算法改进，引入NoPe-NeRF++。它通过相对姿态初始化、局部联合优化和全局优化阶段，提高姿态估计的准确性并提升NeRF表示的质量。该方法结合了局部和全局线索，提高了姿态估计的准确性和新颖视图合成的性能。

Key Takeaways

NoPe-NeRF++是一种针对Neural Radiance Fields (NeRF)的新型局部到全局优化算法。
该方法解决了现有方法（如NoPe-NeRF）在复杂场景中恢复相机姿态的困难。
NoPe-NeRF++通过相对姿态初始化、局部联合优化和全局优化阶段，提高了姿态估计的准确性。
首次将局部和全局线索无缝结合到NeRF中。
该方法在姿态估计准确性和新颖视图合成方面表现出卓越性能。
在基准数据集上的广泛评估证明了其优越性能和稳健性，即使在具有挑战性的场景中也是如此。

Cool Papers

点此查看论文截图

Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis

Authors:Kang Yang, Yuning Chen, Wan Du

We present GRaF, Generalizable Radio-Frequency (RF) Radiance Fields, a framework that models RF signal propagation to synthesize spatial spectra at arbitrary transmitter or receiver locations, where each spectrum measures signal power across all surrounding directions at the receiver. Unlike state-of-the-art methods that adapt vanilla Neural Radiance Fields (NeRF) to the RF domain with scene-specific training, GRaF generalizes across scenes to synthesize spectra. To enable this, we prove an interpolation theory in the RF domain: the spatial spectrum from a transmitter can be approximated using spectra from geographically proximate transmitters. Building on this theory, GRaF comprises two components: (i) a geometry-aware Transformer encoder that captures spatial correlations from neighboring transmitters to learn a scene-independent latent RF radiance field, and (ii) a neural ray tracing algorithm that estimates spectrum reception at the receiver. Experimental results demonstrate that GRaF outperforms existing methods on single-scene benchmarks and achieves state-of-the-art performance on unseen scene layouts.

我们提出了GRaF，即通用射频（RF）辐射场（Generalizable Radio-Frequency Radiance Fields），这是一个模型射频信号传播的框架，用于合成任意发射机或接收机位置的频谱，其中每个频谱测量接收器周围所有方向的信号功率。不同于最新方法使用场景特定的训练将普通神经辐射场（NeRF）适应到射频领域，GRaF可以在多个场景中进行通用化以合成频谱。为此，我们在射频领域证明了一种插值理论：发射机的频谱可以通过地理上相近的发射机的频谱来近似。基于这一理论，GRaF包含两个组件：（i）一个几何感知的Transformer编码器，能够从邻近发射机捕获空间相关性，以学习独立于场景的潜在射频辐射场；（ii）一种神经光线追踪算法，用于估算接收器的频谱接收情况。实验结果表明，GRaF在单场景基准测试中优于现有方法，并在未见场景布局上达到了最新技术水平。

论文及项目相关链接

PDF

Summary

GRaF是一种通用射频（RF）辐射场框架，用于模拟射频信号传播并合成任意发射机或接收机位置的频谱。它通过利用邻近发射机的空间相关性，学习一个与场景无关的潜在RF辐射场，并通过神经网络追踪算法估计接收机的频谱接收情况。实验结果表明，GRaF在单场景基准测试中优于现有方法，并在未见场景布局上达到最新技术水平。

Key Takeaways