1. What are the contributions in "Simplifying complex environments using incremental textured depth meshes" ?
The authors present an incremental algorithm to compute image-based simplifications of a large environment.. The authors use an optimization-based approach to generate samples based on scene visibility, and from each viewpoint create textured depth meshes ( TDMs ) using sampled range panoramas of the environment.. The authors also present an encoding scheme for multiple TDMs that exploits spatial coherence among different viewpoints.
read more
2. What are the future works mentioned in the paper "Simplifying complex environments using incremental textured depth meshes" ?
Their preliminary results are encouraging: the authors are able to render the complex 13 million powerplant model at more than 20 frames a second on a single PC with very few visual artifacts ( as shown in the video ).. There are many directions for future work.. The large arrays of pipes in this model are a challenge for any rendering acceleration algorithm and highlight the potential of their approach.. The extension to three dimensions is relatively straightforward: since the objective function is defined at all points, the authors would need to compute candidate points using the 3D Voronoi diagram of existing sample locations instead of the 2D version.
read more





