Traditional Radiance Field (RF) representations capture details of a specific scene and must be trained afresh on each scene. Semantic feature fields have been added to RFs to facilitate several segmentation tasks. Generalised RF representations learn the principles of view interpolation. A generalised RF can render new views of an unknown and untrained scene, given a few views. We present a way to distil feature fields into the generalised GNT representation. Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features. This enables multi-view segmentation of arbitrary new scenes. We show different semantic features being distilled into generalised RFs. Our multi-view segmentation results are on par with methods that use traditional RFs. GSN closes the gap between standard and generalisable RF methods significantly. Project Page: https://vinayak-vg.github.io/GSN/

翻译：摘要：传统辐射场表示能捕获特定场景的细节，但需对每个场景重新训练。语义特征场已被引入辐射场以支持多项分割任务。泛化辐射场表示学习视角插值原理，给定少量视角即可渲染未知、未训练场景的新视角。我们提出了一种将特征场蒸馏到泛化GNT表示中的方法。我们的GSN表示能实时生成未见场景的新视角，并附带一致的逐像素语义特征，从而实现对任意新场景的多视角分割。我们展示了将不同语义特征蒸馏到泛化辐射场中的过程。实验结果表明，我们的多视角分割结果可与使用传统辐射场的方法相媲美。GSN显著缩小了标准方法与泛化辐射场方法之间的差距。项目页面：https://vinayak-vg.github.io/GSN/