辐射场表面物点引导的主动视图选择  

Active view selection for radiance fields using surface object points

作　　者：谢文想 许威威 XIE Wenxiang;XU Weiwei(College of Computer Science and Technology,Zhejiang University,Hangzhou Zhejiang 310000,China)

机构地区：[1]浙江大学计算机科学与技术学院,浙江杭州310000

出　　处：《图学学报》2025年第1期179-187,共9页Journal of Graphics

基　　金：浙江省“尖兵”“领雁”研发攻关计划(2023C01181)。

摘　　要：神经辐射场(NeRF)的出现显著提高了新视图渲染和3D重建的质量,但其数据收集过程仍然依赖于人工经验,这限制了在未知环境探索和规划等任务上的应用,因此,如何有效选择最具信息增益的视图变得至关重要,为此提出了一种新的主动视图选择策略。首先,通过体渲染权重获取训练光线投射到场景表面附近的三维点,然后计算每个三维点对于候选视图的可见性,并使用光度置信度加权来衡量候选视图,最终选择可见三维点较少且置信度低的候选视图作为新的训练视图。在Blender数据集上的实验表明,与现有的方法相比,该方法在下一最佳视图和下一批最佳视图选择上分别提高了3.88 dB和5.88 dB的PSNR质量,同时视图选择速度提高近30倍。Neural radiance fields(NeRF)has significantly enhanced the quality of novel view synthesis and 3D reconstruction.However,the data collection process for NeRF training still relies on manual experience,which limits its applications in tasks such as unknown environment exploration and planning.Therefore,it becomes crucial to effectively select views with the highest information gain for training.A novel active view selection strategy was proposed to address this.Firstly,volume rendering weights were utilized to obtain 3D points near the surface of the scene where training rays were projected.Then,the visibility of each 3D point for candidate views was calculated,and photometric confidence weighting was employed to measure the candidate views.Finally,candidate views with fewer visible 3D points and lower confidence were selected as the new training views.Experiments on the Blender datasets demonstrated that our approach achieved a PSNR improvement of 3.88 dB and 5.88 dB for single-view and batch view selections,respectively,compared with existing methods,and increased view selection speed by nearly 30 times.

关 键 词：神经渲染 神经辐射场 主动视图选择 场景感知 未知环境探索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]