Efficient View Path Planning for Autonomous Implicit Reconstruction

Implicit neural representations have shown promising potential for 3D scene reconstruction. Recent work applies it to autonomous 3D reconstruction by learning information gain for view path planning. Effective as it is, the computation of the information gain is expensive, and compared with that using volumetric representations, collision checking using the implicit representation for a 3D point is much slower. In the paper, we propose to 1) leverage a neural network as an implicit function approximator for the information gain field and 2) combine the implicit fine-grained representation with coarse volumetric representations to improve efficiency. Further with the improved efficiency, we propose a novel informative path planning based on a graph-based planner. Our method demonstrates significant improvements in the reconstruction quality and planning efficiency compared with autonomous reconstructions with implicit and explicit representations. We deploy the method on a real UAV and the results show that our method can plan informative views and reconstruct a scene with high quality.

Authors

• Jing Zeng
• Yanxu Li
• Yunlong Ran
• Shuo Li
• Fei Gao
• Lincheng Li
• Shibo He
• Jiming Chen 0001
• Qi Ye 0001

Keywords

• Three-dimensional displays
• Costs
• Automation
• Shape
• Robot vision systems
• Neural networks
• Cameras
• Path Planning
• Implicit Reconstruction
• 3D Reconstruction
• Information Gain
• 3D Point
• Implicit Function
• Reconstruction Quality
• Explicit Representation
• Collision Detection
• 3D Scene
• Implicit Representation
• Path Information
• Path Length
• Image Size
• Multilayer Perceptron
• Efficacy Of Method
• Particle Filter
• Optimal Path
• Planning Methods
• Planning Time
• Rapidly-exploring Random Tree
• Reconstruction Step
• Occupancy Map
• Sampling-based Methods
• Reconstruction Module
• Start Node
• Camera Pose
• Ranking Of Factors
• Gain Factor
• Voxel Resolution