Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction
CoRR, pp. 4065-4074, 2019.
We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the "ground truth" surface normals in the training set to ensure consistency with the semantic labels; (2) concurrently train on a mix ...More
PPT (Upload PPT)