SlimmeRF：可调节的辐射场

摘要

最近，神经辐射场（Neural Radiance Field，NeRF）及其变种已成为新视角合成和3D场景重建的成功方法。然而，大多数当前的NeRF模型要么通过使用大模型尺寸实现高准确性，要么通过牺牲准确性来实现高内存效率。这限制了任何单个模型的适用范围，因为高准确性模型可能无法适应低内存设备，而内存高效模型可能无法满足高质量要求。为此，我们提出了SlimmeRF，这是一种模型，通过精简，允许在模型尺寸和准确性之间进行即时的测试时间权衡，从而使模型同时适用于具有不同计算预算的场景。我们通过一种新提出的算法，名为张量秩增加（Tensorial Rank Incrementation，TRaIn），在训练过程中逐渐增加模型张量表示的秩来实现这一目标。我们还观察到，我们的模型在稀疏视图场景中允许更有效的权衡，有时甚至在精简后实现更高的准确性。我们将这归因于错误信息（如浮点值）往往存储在对应于较高秩的组件中。我们的实现可在https://github.com/Shiran-Yuan/SlimmeRF 上找到。

English

Neural Radiance Field (NeRF) and its variants have recently emerged as successful methods for novel view synthesis and 3D scene reconstruction. However, most current NeRF models either achieve high accuracy using large model sizes, or achieve high memory-efficiency by trading off accuracy. This limits the applicable scope of any single model, since high-accuracy models might not fit in low-memory devices, and memory-efficient models might not satisfy high-quality requirements. To this end, we present SlimmeRF, a model that allows for instant test-time trade-offs between model size and accuracy through slimming, thus making the model simultaneously suitable for scenarios with different computing budgets. We achieve this through a newly proposed algorithm named Tensorial Rank Incrementation (TRaIn) which increases the rank of the model's tensorial representation gradually during training. We also observe that our model allows for more effective trade-offs in sparse-view scenarios, at times even achieving higher accuracy after being slimmed. We credit this to the fact that erroneous information such as floaters tend to be stored in components corresponding to higher ranks. Our implementation is available at https://github.com/Shiran-Yuan/SlimmeRF.

SlimmeRF：可调节的辐射场

SlimmeRF: Slimmable Radiance Fields

摘要

Support