3D scene segmentation based on neural implicit representation has emerged recently with the advantage of training only on 2D supervision. However, existing approaches still requires expensive per-scene optimization that prohibits generalization to novel scenes during inference. To circumvent this problem, we introduce a generalizable 3D segmentation framework based on implicit representation. Specifically, our framework takes in multi-view image features and semantic maps as the inputs instead of only spatial information to avoid overfitting to scene-specific geometric and semantic information. We propose a novel soft voting mechanism to aggregate the 2D semantic information from different views for each 3D point. In addition to the image features, view difference information is also encoded in our framework to predict the voting scores. Intuitively, this allows the semantic information from nearby views to contribute more compared to distant ones. Furthermore, a visibility module is also designed to detect and filter out detrimental information from occluded views. Due to the generalizability of our proposed method, we can synthesize semantic maps or conduct 3D semantic segmentation for novel scenes with solely 2D semantic supervision. Experimental results show that our approach achieves comparable performance with scene-specific approaches. More importantly, our approach can even outperform existing strong supervision-based approaches with only 2D annotations. Our source code is available at: https://github.com/HLinChen/GNeSF.

翻译：基于神经隐式表示的三维场景分割近期出现，其优势在于仅需二维监督训练。然而现有方法仍需要昂贵的逐场景优化，导致推理时无法泛化到新场景。为解决该问题，我们提出一种基于隐式表示的可泛化三维分割框架。具体而言，该框架以多视图图像特征和语义图作为输入（而非仅空间信息），从而避免过拟合于场景特定的几何与语义信息。我们提出一种新型软投票机制，用于聚合不同视角下每个三维点的二维语义信息。除图像特征外，视差信息也被编码至框架中以预测投票分数。直观而言，这使近邻视角的语义信息比远处视角贡献更大。此外，我们还设计了可见性模块，用于检测并过滤来自遮挡视角的有害信息。凭借所提方法的可泛化性，我们仅需二维语义监督即可为新场景合成语义图或执行三维语义分割。实验结果表明，该方法达到了与场景特定方法相当的性能。更重要的是，该方法仅使用二维标注即可超越现有强监督方法。源代码已开源：https://github.com/HLinChen/GNeSF。