Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
This work addresses efficiency in scene modeling for indoor novel view synthesis, which is incremental as it builds on existing subset selection methods with a new diversity-driven approach.
The paper tackles the problem of redundant information in monocular video sequences for indoor novel view synthesis by formulating it as a combinatorial optimization task for view subset selection, achieving consistent outperformance of baseline strategies while using only 5-20% of the data.
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 utility functions. We provide a theoretical analysis of these utility 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. Experiments on IndoorTraj show that our framework consistently outperforms baseline strategies while using only 5-20% of the data, highlighting its remarkable efficiency and effectiveness. The code is available at: https://github.com/zehao-wang/IndoorTraj