Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos
arxiv(2020)
摘要
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The predicted depth, egomotion, and camera intrinsics are used to provide an additional supervision signal to the segmentation model, significantly enhancing its quality, or, alternatively, reducing the number of labels the segmentation model needs. Our experiments were performed on the ScanNet dataset.
更多查看译文
关键词
semantic segmentation,videos,spatio-temporal
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络