Neural Radiance Fields, or NeRFs, have drastically improved novel view
synthesis and 3D reconstruction for rendering. NeRFs achieve impressive results
on object-centric reconstructions, but the quality of novel view synthesis with
free-viewpoint navigation in complex environments (rooms, houses, etc) is often
problematic.
While algorithmic improvements play an important role in the resulting
quality of novel view synthesis, in this work, we show that because optimizing
a NeRF is inherently a data-driven process, good quality data play a
fundamental role in the final quality of the reconstruction. As a consequence,
it is critical to choose the data samples -- in this case the cameras -- in a
way that will eventually allow the optimization to converge to a solution that
allows free-viewpoint navigation with good quality.
Our main contribution is an algorithm that efficiently proposes new camera
placements that improve visual quality with minimal assumptions. Our solution
can be used with any NeRF model and outperforms baselines and similar work.

优化 NeRF 模型时，良好的数据样本和有效的相机位置选择对于最终重建的可视化质量至关重要。本研究提出了一种算法，能够以最少的假设来提供改善可视化质量的新相机位置，并在各方面优于基线和类似方法。

通过渐进相机布置提升 NeRF 在复杂环境中的质量

Improving NeRF Quality by Progressive Camera Placement for Unrestricted  Navigation in Complex Environments

Driving risk prediction has been a topic of much research over the past few
decades to minimize driving risk and increase safety. The use of demographic
information in risk prediction is a traditional solution with applications in
insurance planning, however, it is difficult to capture true driving behavior
via such coarse-grained factors. Therefor, the use of telematics data has
gained a widespread popularity over the past decade. While most of the existing
studies leverage demographic information in addition to telematics data, our
objective is to maximize the use of telematics as well as contextual
information (e.g., road-type) to build a risk prediction framework with
real-world applications. We contextualize telematics data in a variety of
forms, and then use it to develop a risk classifier, assuming that there are
some weak risk labels available (e.g., past traffic citation records). Before
building a risk classifier though, we employ a novel data-driven process to
augment weak risk labels. Extensive analysis and results based on real-world
data from multiple major cities in the United States demonstrate usefulness of
the proposed framework.

利用遥测数据和上下文信息构建驾驶风险预测框架，采用数据驱动过程增强风险标签，并在真实数据中进行验证。