Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos

11 Apr 2020  ·  Ankita Pasad, Ariel Gordon, Tsung-Yi Lin, Anelia Angelova ·

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.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here