无需训练，通过光线映射差异实时识别动态物体，提升3D重建精度。
RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction
- 利用光线映射与图像预测的差异，推理动态区域。
- 在多个基准上达到流式重建最优性能，避免运动伪影和轨迹漂移。
- 适合需要实时高精度3D重建的自动驾驶、机器人场景。
流式前馈3D重建可实时光学估计场景几何与相机位姿，但缺乏显式动态建模时易受移动物体影响，导致伪影与漂移。本文提出无训练的流式动态场景重建框架RayMap3R。观察到基于光线映射的预测存在静态场景偏差，这为动态识别提供了内部线索。据此设计双分支推理机制，通过对比光线映射与图像预测，识别动态区域并抑制其对记忆更新的干扰。进一步引入重置度量对齐与状态感知平滑，以保持度量一致性并稳定轨迹预测。该方法在多个基准上实现流式重建最优性能，显著提升动态场景下的重建质量。
原文摘要 · Abstract (English)
Streaming feed-forward 3D reconstruction enables real-time joint estimation of scene geometry and camera poses from RGB images. However, without explicit dynamic reasoning, streaming models can be affected by moving objects, causing artifacts and drift. In this work, we propose RayMap3R, a training-free streaming framework for dynamic scene reconstruction. We observe that RayMap-based predictions exhibit a static-scene bias, providing an internal cue for dynamic identification. Based on this observation, we construct a dual-branch inference scheme that identifies dynamic regions by contrasting RayMap and image predictions, suppressing their interference during memory updates. We further introduce reset metric alignment and state-aware smoothing to preserve metric consistency and stabilize predicted trajectories. Our method achieves state-of-the-art performance among streaming approaches on dynamic scene reconstruction across multiple benchmarks.
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。