The explicit neural radiance field (NeRF) has gained considerable interest
for its efficient training and fast inference capabilities, making it a
promising direction such as virtual reality and gaming. In particular,
PlenOctree (POT)[1], an explicit hierarchical multi-scale octree
representation, has emerged as a structural and influential framework. However,
POT's fixed structure for direct optimization is sub-optimal as the scene
complexity evolves continuously with updates to cached color and density,
necessitating refining the sampling distribution to capture signal complexity
accordingly. To address this issue, we propose the dynamic PlenOctree DOT,
which adaptively refines the sample distribution to adjust to changing scene
complexity. Specifically, DOT proposes a concise yet novel hierarchical feature
fusion strategy during the iterative rendering process. Firstly, it identifies
the regions of interest through training signals to ensure adaptive and
efficient refinement. Next, rather than directly filtering out valueless nodes,
DOT introduces the sampling and pruning operations for octrees to aggregate
features, enabling rapid parameter learning. Compared with POT, our DOT
outperforms it by enhancing visual quality, reducing over $55.15$/$68.84\%$
parameters, and providing 1.7/1.9 times FPS for NeRF-synthetic and Tanks $\&$
Temples, respectively. Project homepage:this https URL
[1] Yu, Alex, et al. "Plenoctrees for real-time rendering of neural radiance
fields." Proceedings of the IEEE/CVF International Conference on Computer
Vision. 2021.

提出了一种动态的 PlenOctree DOT 方法，通过自适应细化采样分布来适应不断变化的场景复杂度，并通过层次化特征融合策略提高了视觉质量，减少了参数数量并提供了更高的帧率。

动态 PlenOctree 在显式 NeRF 中的自适应采样细化

Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF

We propose an efficient method for rendering complex luminaires using a
high-quality octree-based representation of the luminaire emission. Complex
luminaires are a particularly challenging problem in rendering, due to their
caustic light paths inside the luminaire. We reduce the geometric complexity of
luminaires by using a simple proxy geometry and encode the visually-complex
emitted light field by using a neural radiance field. We tackle the multiple
challenges of using NeRFs for representing luminaires, including their high
dynamic range, high-frequency content and null-emission areas, by proposing a
specialized loss function. For rendering, we distill our luminaires' NeRF into
a Plenoctree, which we can be easily integrated into traditional rendering
systems. Our approach allows for speed-ups of up to 2 orders of magnitude in
scenes containing complex luminaires introducing minimal error.

使用基于八叉树的高质量光源表达方法及神经辐射场技术，以简化的代理几何以及专门的损失函数为多光源的复杂场景提供渲染加速，并将其蒸馏为 Plenoctree 以快速集成到传统渲染系统。