Qixing Huang: Extreme Relative Pose Estimation via Scene Completion скачать в хорошем качестве

Qixing Huang: Extreme Relative Pose Estimation via Scene Completion

Estimating the relative rigid pose between two RGB-D scans of the same underlying environment is a fundamental problem in computer vision, robotics, and computer graphics. Most existing approaches allow only limited relative pose changes since they require considerable overlap between the input scans. This talk discusses techniques extending the scope to extreme relative poses, with little or no overlap between the input scans. The key idea is to infer complete scene information about the underlying environment and match the completed scans. We discuss suitable representations for scene completion and how to integrate relative pose estimation and scene completion. Experimental results on benchmark datasets show that our approach leads to considerable improvements over state-of-the-art methods for relative pose estimation. In particular, our approach provides encouraging relative pose estimates even between non-overlapping scans.