ASIST: Automatic Semantically Invariant Scene Transformation
This work addresses scene transformation for applications in virtual reality, scan repair, and robotics, but appears incremental as it builds on existing object replacement techniques.
The paper tackles the problem of transforming point clouds by replacing objects with semantically equivalent counterparts, and presents ASIST, a method that achieves this through a unified optimization framework for semantic labeling and object replacement.
We present ASIST, a technique for transforming point clouds by replacing objects with their semantically equivalent counterparts. Transformations of this kind have applications in virtual reality, repair of fused scans, and robotics. ASIST is based on a unified formulation of semantic labeling and object replacement; both result from minimizing a single objective. We present numerical tools for the efficient solution of this optimization problem. The method is experimentally assessed on new datasets of both synthetic and real point clouds, and is additionally compared to two recent works on object replacement on data from the corresponding papers.