发表机构
School of Artificial Intelligence and Robotics, Hunan University; I3A, Universidad de Zaragoza; Agricultural Information Institute, Chinese Academy of Agricultural Sciences（湖南大学人工智能与机器人学院; 萨拉戈萨大学I3A研究所; 中国农业科学院农业信息研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ZipMVS是一种压缩代价体的多视图立体匹配方法，可在保持重建精度的同时降低GPU内存消耗，在相关数据集上实现了重建质量与内存使用的良好平衡。
AI 中文摘要
多视图立体匹配（MVS）方法可从多张已配准的RGB图像生成高精度三维重建结果，这得益于图像间丰富的几何约束。然而，其巨大的内存需求仍是在航空航天、自主系统等对资源效率要求极高的领域部署的主要障碍。本研究提出ZipMVS，一种专为高效高质量重建设计的MVS方法。我们提出一种新颖的深度假设策略，可大幅压缩代价体，从而在保持重建精度的同时显著降低GPU内存消耗。在DTU和Tanks and Temples数据集上的实验表明，ZipMVS与其他面向效率的MVS方法相比，重建质量具有竞争力，且在重建质量与GPU内存使用间实现了有竞争力的平衡。代码可在指定URL获取。
英文摘要
Multi-view stereo (MVS) methods typically deliver highly accurate 3D reconstructions from multiple registered RGB images, thanks to the highly informative, geometric constraints between them. However, their substantial memory requirements remain a major obstacle for deployment in domains such as aerospace and autonomous systems, where resource efficiency is critical. In this work, we introduce ZipMVS, an MVS method specifically designed for efficient high-quality reconstruction. We propose a novel depth-hypothesis strategy that enables substantial compression of the cost volume, hence greatly reducing GPU memory consumption while preserving reconstruction accuracy. Experiments on the DTU and Tanks and Temples datasets show that ZipMVS achieves competitive reconstruction quality compared with other efficiency-oriented MVS methods, while achieving a competitive balance between reconstruction quality and GPU memory usage. The code is available at https://github.com/JihnGlyn/ZipMVS
Comments14 pages, 8 figures
