Automatic surgical instruction generation is a prerequisite towards intra-operative context-aware surgical assistance.
Existing works usually estimate the missing shape by decoding a latent feature encoded from the input points.
The experiment results demonstrate the ability of our method on capturing long-term frame dependencies, which largely outperform the state-of-the-art methods on the frame-wise accuracy up to ~6 points and the F1@50 score ~6 points.
Semantic reconstruction of indoor scenes refers to both scene understanding and object reconstruction.
Ranked #2 on Room Layout Estimation on SUN RGB-D (using extra training data)
Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling.
In vivo laparoscopic videos used in the tests have demonstrated the robustness and accuracy of our proposed framework on both camera tracking and surface reconstruction, illustrating the potential of our algorithm for depth augmentation and depth-corrected augmented reality in MIS with monocular endoscopes.