面向相机视角选择的覆盖度优化
Coverage Optimization for Camera View Selection
提出一种轻量、可解释的覆盖度指标 CONVERGE，用于主动视角选择：它用费舍尔信息增益的可解近似替代昂贵的透射率估计，可直接接入 Nerfstudio 的采集流程，提升 NeRF 类辐射场在固定或具身采集场景下的重建质量。
原文依据 This leads to a lightweight coverage-based view selection metric that avoids expensive transmittance estimation and is robust to noise and training dynamics.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论什么样的视角才算好视角？用于学习三维重建的数据质量，对于实现高效且准确的三维场景建模至关重要。本文研究主动视角选择问题，并给出一种有原理依据的分析，由此得到一个简单且可解释的准则，用于挑选信息量大的相机位姿。我们的关键洞见是：信息量大的视角可以通过最小化费舍尔信息增益的一个可解近似来获得，而该近似最终归结为偏好那些覆盖了此前相机观测不足的几何区域的视角。由此得到一个轻量的、基于覆盖度的视角选择指标，它避免了代价高昂的透射率估计，并且对噪声和训练动态具有鲁棒性。我们将该指标称为 CONVERGE（Coverage Optimized Novel Viewset Estimation for Reconstructing Geometry Efficiently，即面向高效几何重建的覆盖度优化新视角集合估计）。我们把该方法集成到 Nerfstudio 框架中，并在固定采集与具身采集两种场景下于真实数据集上进行了评测。在多个数据集和多种辐射场基线上，与最优的主动视角选择方法相比，我们的方法都能稳定提升重建质量。
英文原文摘要 1142 字符
What makes a good viewpoint? The quality of the data used to learn 3D reconstructions is crucial for enabling efficient and accurate scene modeling. We study the active view selection problem and develop a principled analysis that yields a simple and interpretable criterion for selecting informative camera poses. Our key insight is that informative views can be obtained by minimizing a tractable approximation of the Fisher Information Gain, which reduces to favoring viewpoints that cover geometry that has been insufficiently observed by past cameras. This leads to a lightweight coverage-based view selection metric that avoids expensive transmittance estimation and is robust to noise and training dynamics. We call this metric CONVERGE (Coverage Optimized Novel Viewset Estimation for Reconstructing Geometry Efficiently). We integrate our method into the Nerfstudio framework and evaluate it on real datasets within fixed and embodied data acquisition scenarios. Across multiple datasets and radiance-field baselines, our method consistently improves reconstruction quality compared to state-of-the-art active view selection methods.