单目视频实时重建3D场景，无需计算相机参数
SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos
- 用滑动窗口切分视频，直接从图像回归局部点云
- 在20+帧率下实现顶尖重建精度与完整性
- 适合需要轻量实时三维重建的应用场景
本文提出SLAM3R，一种基于单目RGB视频的实时高精度稠密3D重建系统。该系统通过前馈神经网络无缝集成局部三维重建与全局坐标注册，实现端到端处理。输入视频经滑动窗口机制分割为重叠片段，系统直接从每段图像回归3D点云，并逐步对齐与形变这些局部点云，生成全局一致的场景重建，全程无需显式求解相机参数。在多个数据集上的实验表明，SLAM3R在保持20+ FPS实时性能的同时，实现了当前最优的重建精度与完整性。代码已开源：https://github.com/PKU-VCL-3DV/SLAM3R。
原文摘要 · Abstract (English)
In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a globally consistent scene reconstruction - all without explicitly solving any camera parameters. Experiments across datasets consistently show that SLAM3R achieves state-of-the-art reconstruction accuracy and completeness while maintaining real-time performance at 20+ FPS. Code available at: https://github.com/PKU-VCL-3DV/SLAM3R.
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。