An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deployment data, adapting the model on the new scenes is often crucial to obtain good performance. In this work, we study continual multi-scene adaptation for the task of semantic segmentation, assuming that no ground-truth labels are available during deployment and that performance on the previous scenes should be maintained. We propose training a Semantic-NeRF network for each scene by fusing the predictions of a segmentation model and then using the view-consistent rendered semantic labels as pseudo-labels to adapt the model. Through joint training with the segmentation model, the Semantic-NeRF model effectively enables 2D-3D knowledge transfer. Furthermore, due to its compact size, it can be stored in a long-term memory and subsequently used to render data from arbitrary viewpoints to reduce forgetting. We evaluate our approach on ScanNet, where we outperform both a voxel-based baseline and a state-of-the-art unsupervised domain adaptation method.

本文研究了语义分割的连续多场景自适应问题，提出了基于 Semantic-NeRF 网络的解决方案，通过将分割模型的预测结果融合，使用视点一致的渲染语义标签来适应模型。我们在 ScanNet 数据集上测试，取得了比基线和最先进的无监督域自适应方法更好的性能。

基于神经渲染的无监督连续语义适应