Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
Abstract: Novel view synthesis of indoor scenes can be achieved by capturing a monocular video sequence of the environment. However, redundant information caused by artificial movements in the input video data reduces the efficiency of scene modeling. To address this, we formulate the problem as a combinatorial optimization task for view subset selection. In this work, we propose a novel subset selection framework that integrates a comprehensive diversity-based measurement with well-designed metric functions. We provide a theoretical analysis of these metric functions and validate their effectiveness through extensive experiments. Furthermore, we introduce IndoorTraj, a novel dataset designed for indoor novel view synthesis, featuring complex and extended trajectories that simulate intricate human behaviors. Remarkably, experiments on IndoorTraj demonstrate that our framework consistently outperforms baseline strategies using only 5-20\% of the data.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Adam_W_Harley1
Submission Number: 4134
Loading