Inter-Frame Predictive Contour Coding for Semantic Map Compression

Dynamic semantic maps have become an important intermediate representation for many computer vision applications. Efficient lossless compression of such maps is essential for reducing storage and transmission costs. Existing contour-based semantic map compression methods mainly exploit spatial redundancy within individual frames while largely ignoring the strong temporal correlation between adjacent semantic maps. In this paper, we propose an inter-frame predictive contour coding framework for lossless semantic map compression. The proposed framework first predicts blob positions and label indexes from the reference frame and then performs contour prediction using corresponding chain-code units in the reference contours. A mode selection mechanism is further employed to choose between intra and inter coding according to the estimated coding cost. By exploiting temporal contour redundancy while preserving the advantages of contour-based representation, the proposed framework significantly improves coding efficiency. Experimental results on the VSPW dynamic semantic segmentation dataset demonstrate that the proposed method consistently outperforms state-of-the-art lossless semantic map compression methods. Compared with the recent context-adaptive extended chain coding framework, the proposed inter-frame coding achieves an average bitrate reduction of 3.0% without significant increase in the average encoding time, demonstrating an effective trade-off between compression performance and computational complexity. The source code is made publicly available at https://github.com/InterDigitalInc/LosslessSegmentationMapCompression.