English

Diversity-Driven View Subset Selection for Indoor Novel View Synthesis

Computer Vision and Pattern Recognition 2025-05-22 v2 Artificial Intelligence

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 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

Keywords

Cite

@article{arxiv.2409.07098,
  title  = {Diversity-Driven View Subset Selection for Indoor Novel View Synthesis},
  author = {Zehao Wang and Han Zhou and Matthew B. Blaschko and Tinne Tuytelaars and Minye Wu},
  journal= {arXiv preprint arXiv:2409.07098},
  year   = {2025}
}

Comments

12 pages, TMLR 2025

R2 v1 2026-06-28T18:40:51.675Z