Dynamic Warping Network for Semantic Video Segmentation

Figure 4

Qualitative results of consecutive frames on the Cityscapes dataset. Baseline methods: training and inferring on single frames. Warping-based method: adopting the original warping operation to enhance the feature. Our method: utilizing the flow-guided convolution to adaptively warp the interframe features. Compared with the baseline, the warping-based method brings a slight improvement in the moving objects, and our method can produce more accurate and consistent segmentation results.