Revisiting Depth Image Fusion with Variational Message Passing Akihiro Sugimoto


Datum / čas
Date(s) - 01.10.
11:00 - 12:30

Místo konání

Kategorie ne Kategorie


The running average approach has long been perceived as the best choice for fusing depth measurements captured by a consumer-grade RGB-D camera into a global 3D model. This strategy, however, assumes exact correspondences between points in a 3D model and points  in the captured RGB-D images. Such assumption does not hold true in many cases because of errors in motion tracking, noise, occlusions, or inconsistent surface sampling during measurements. Accordingly, reconstructed 3D models suffer unpleasant visual artifacts.  In this talk, we visit the depth fusion problem from a probabilistic viewpoint and formulate it as a probabilistic optimization using variational message passing in a Bayesian network. Our formulation enables us to fuse depth images robustly, accurately, and  fast for high quality RGB-D keyframe creation, even if exact point correspondences are not always available. Our formulation also allows us to smoothly combine depth and color information for further improvements without increasing computational speed. The  quantitative and qualitative comparative evaluation on built keyframes of indoor scenes show that our proposed framework achieves promising results for reconstructing accurate 3D models.


For more information on IMPACT seminars, please visit