用多样性筛选视频帧，仅用5%-20%数据实现高质量室内新视角生成
Diversity-Driven View Subset Selection for Indoor Novel View Synthesis
- 基于多样性度量与实用函数设计新选择框架
- 仅需5%-20%数据即超越基线方法
- 适合需要高效建模的室内场景生成任务
通过捕捉环境的单目视频序列可实现室内场景的新视角合成。然而，输入视频中由人为运动带来的冗余信息降低了场景建模效率。为此，我们将问题建模为视图子集选择的组合优化任务。本文提出一种新颖的子集选择框架，融合全面的多样性度量与精心设计的效用函数，并提供理论分析验证其有效性。此外，我们构建了 IndoorTraj——一个专为室内新视角合成设计的新数据集，包含复杂且长距离轨迹，模拟真实人类行为。在 IndoorTraj 上的实验表明，本框架在仅使用 5%-20% 数据的情况下，持续优于基线策略，展现出卓越的效率与效果。代码已开源：https://github.com/zehao-wang/IndoorTraj
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。