Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility
This addresses the challenge of autonomous 3D mapping in unknown environments, offering an incremental improvement over traditional utility functions.
The paper tackles the problem of efficiently exploring unknown 3D scenes with drones by learning a utility function to predict the usefulness of future viewpoints, showing that it outperforms existing handcrafted methods in reconstruction performance and robustness to sensor noise.
Camera equipped drones are nowadays being used to explore large scenes and reconstruct detailed 3D maps. When free space in the scene is approximately known, an offline planner can generate optimal plans to efficiently explore the scene. However, for exploring unknown scenes, the planner must predict and maximize usefulness of where to go on the fly. Traditionally, this has been achieved using handcrafted utility functions. We propose to learn a better utility function that predicts the usefulness of future viewpoints. Our learned utility function is based on a 3D convolutional neural network. This network takes as input a novel volumetric scene representation that implicitly captures previously visited viewpoints and generalizes to new scenes. We evaluate our method on several large 3D models of urban scenes using simulated depth cameras. We show that our method outperforms existing utility measures in terms of reconstruction performance and is robust to sensor noise.