通过分块重捕技术，大幅降低高分辨率3D重建的显存占用。
Sub-Image Recapture for Multi-View 3D Reconstruction
- 将大图切分为小块独立处理，重构流程无需整体加载
- 相比传统方法显存降低70%以上，支持更大输入分辨率
- 兼容现有算法，适合资源受限场景下的高保真3D重建
高分辨率目标的3D重建因输入图像尺寸过大导致内存需求过高，仍是难题。近年来基于学习的算法虽性能优于传统方法，但通常需要更多内存且存在可扩展性瓶颈。本文提出通用框架子图像重捕获（SIR），将大图像分割为较小子图像并分别处理。该框架使现有3D重建算法可基于子图像重捕获实现，显著降低内存消耗，大幅提升可扩展性。
原文摘要 · Abstract (English)
3D reconstruction of high-resolution target remains a challenge task due to the large memory required from the large input image size. Recently developed learning based algorithms provide promising reconstruction performance than traditional ones, however, they generally require more memory than the traditional algorithms and facing scalability issue. In this paper, we developed a generic approach, sub-image recapture (SIR), to split large image into smaller sub-images and process them individually. As a result of this framework, the existing 3D reconstruction algorithms can be implemented based on sub-image recapture with significantly reduced memory and substantially improved scalability
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。