用多视图大模型提升单目重建精度，实现更稳定的实时三维重建。
M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM
- 在多视图大模型中加入匹配头，生成精细稠密对应关系。
- 相比VGGT-SLAM 2.0，ATE RMSE降低64.3%，ScanNet++上PSNR提升2.11 dB。
- 适合需要高精度单目重建的动态环境应用，如机器人导航与AR。
从未标定的单目视频流进行实时重建仍具挑战，需在动态环境中实现高精度位姿估计与高效在线优化。尽管将3D基础模型与SLAM框架结合是可行方向，但关键瓶颈在于：多数多视图基础模型采用前馈方式估计位姿，生成的像素级对应关系精度不足，难以支撑严格的几何优化。为此，本文提出M^3，通过添加专用匹配头增强多视图基础模型，实现细粒度稠密对应关系，并集成至鲁棒的单目高斯泼溅SLAM系统。M^3还通过动态区域抑制与跨推理内在对齐提升跟踪稳定性。在多样化的室内外基准测试中，其位姿估计与场景重建均达到当前最优水平。特别地，在ScanNet++数据集上，相比VGGT-SLAM 2.0，ATE RMSE降低64.3%；在PSNR上优于ARTDECO 2.11 dB。
原文摘要 · Abstract (English)
Streaming reconstruction from uncalibrated monocular video remains challenging, as it requires both high-precision pose estimation and computationally efficient online refinement in dynamic environments. While coupling 3D foundation models with SLAM frameworks is a promising paradigm, a critical bottleneck persists: most multi-view foundation models estimate poses in a feed-forward manner, yielding pixel-level correspondences that lack the requisite precision for rigorous geometric optimization. To address this, we present M^3, which augments the Multi-view foundation model with a dedicated Matching head to facilitate fine-grained dense correspondences and integrates it into a robust Monocular Gaussian Splatting SLAM. M^3 further enhances tracking stability by incorporating dynamic area suppression and cross-inference intrinsic alignment. Extensive experiments on diverse indoor and outdoor benchmarks demonstrate state-of-the-art accuracy in both pose estimation and scene reconstruction. Notably, M^3 reduces ATE RMSE by 64.3% compared to VGGT-SLAM 2.0 and outperforms ARTDECO by 2.11 dB in PSNR on the ScanNet++ dataset.
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。