用带透明度的矩形表示3D平面，实现精确边界与连续表面重建。
AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
- 将3D平面建模为带alpha通道的矩形，融合2D与3D表示优势。
- 在ScanNet上达到当前最优性能，完整重建具有清晰边界的平面。
- 适合需要高精度3D平面重建的场景，如AR/VR与机器人导航。
我们提出AlphaTablets，一种新型通用的3D平面表示方法，具备连续3D表面与精确边界定义能力。通过将3D平面表示为带有透明度通道的矩形，该方法结合了现有2D与3D平面表示的优势，实现了准确、一致且灵活的3D平面建模。我们在AlphaTablets基础上构建可微分渲染，高效地将3D平面投影至图像，并提出一种新颖的自下而上的单目视频3D平面重建流水线。从2D超像素和预训练模型提供的几何线索出发，初始化为AlphaTablets并基于可微分渲染进行优化。引入有效的合并机制以促进AlphaTablets的增长与精炼。通过迭代优化与合并，成功重建出具有完整表面与清晰边界的3D平面。在ScanNet数据集上的大量实验表明，该方法在3D平面重建任务中达到当前最优性能，充分展现了AlphaTablets作为通用3D平面表示在各类应用中的巨大潜力。项目主页：https://hyzcluster.github.io/alphatablets
原文摘要 · Abstract (English)
We introduce AlphaTablets, a novel and generic representation of 3D planes that features continuous 3D surface and precise boundary delineation. By representing 3D planes as rectangles with alpha channels, AlphaTablets combine the advantages of current 2D and 3D plane representations, enabling accurate, consistent and flexible modeling of 3D planes. We derive differentiable rasterization on top of AlphaTablets to efficiently render 3D planes into images, and propose a novel bottom-up pipeline for 3D planar reconstruction from monocular videos. Starting with 2D superpixels and geometric cues from pre-trained models, we initialize 3D planes as AlphaTablets and optimize them via differentiable rendering. An effective merging scheme is introduced to facilitate the growth and refinement of AlphaTablets. Through iterative optimization and merging, we reconstruct complete and accurate 3D planes with solid surfaces and clear boundaries. Extensive experiments on the ScanNet dataset demonstrate state-of-the-art performance in 3D planar reconstruction, underscoring the great potential of AlphaTablets as a generic 3D plane representation for various applications. Project page is available at: https://hyzcluster.github.io/alphatablets
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。