GRF-Recon：用于长序列前馈重建的全局射线场优化
GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction
浏览论文内容
中文总结 AI 辅助
提出GRF-Recon统一框架，通过从粗到细轨迹对齐、LoRA几何先验注入及混合权重稀疏射线场优化，实现长单目序列的稳定可扩展前馈三维重建，有效减少漂移并保持全局一致性。
中文摘要 AI 辅助
前馈三维重建为从图像序列进行场景建模提供了一种高效范式。将这些模型扩展到大规模单目场景受到过多GPU内存占用、局部几何退化以及长期轨迹漂移的制约。现有的基于分块的优化策略提供的几何约束有限，且无法在扩展轨迹上维持全局一致性。我们提出了一个统一框架，用于从长单目序列中进行稳定且可扩展的前馈三维重建。我们的方法建立在由轻量级几何先验注入增强的从粗到细的轨迹对齐之上。通过LoRA适配将单目几何线索蒸馏进前馈主干网络，在保持推理效率的同时提高了精细结构上的深度精度。我们引入了一种混合权重的稀疏射线场优化，利用高频几何特征来引导局部点云细化并强制执行一致的帧间射线约束。与先前的基于分块的方法不同，这建立了强大的跨帧几何耦合，同时保持了可扩展性。最后，一种结合联合射线误差优化的高效轨迹拼接策略显式地减少了累积漂移。大量实验表明，我们的方法在轨迹精度上与代表性SLAM系统相比具有竞争力，同时在大规模场景中保持了全局一致的三维重建。
英文摘要
Feed-forward 3D reconstruction provides an efficient paradigm for scene modeling from image sequences. Scaling these models to large monocular scenarios are constrained by excessive GPU memory footprint, degraded local geometry, and long-term trajectory drift. Existing chunk-based optimization strategies provide limited geometric constraints and fail to maintain global consistency over extended trajectories. We present a unified framework for stable and scalable feed-forward 3D reconstruction from long monocular sequences. Our approach builds on coarse-to-fine trajectory alignment augmented by lightweight geometric prior injection. Distilling monocular geometric cues into the feed-forward backbone via LoRA adaptation improves depth accuracy on fine structures while preserving inference efficiency. We introduce a hybrid-weight sparse ray-field optimization that leverages high-frequency geometric features to guide local point-cloud refinement and enforce consistent inter-frame ray constraints. Unlike prior chunk-based methods, this establishes strong cross-frame geometric coupling while maintaining scalability. Finally, an efficient trajectory stitching strategy with joint ray-error optimization explicitly reduces accumulated drift. Extensive experiments show that our approach achieves competitive trajectory accuracy compared with representative SLAM systems, while maintaining globally consistent 3D reconstruction in large-scale scenarios.
发表机构
- College of Information Science and Engineering, Northeastern University（东北大学信息科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。
