DAGE通过双流架构实现高分辨率视频几何估计，兼顾精度与效率。
DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
- 双流设计：低分辨率流建全局一致性，高分辨率流保留细节
- 支持2K输入，长序列仍保持视角一致性和精准相机位姿
- 轻量级融合模块不破坏预训练单帧路径，适合实时应用
从非标定多视角/视频输入中准确估计几何结构和相机位姿仍是挑战，尤其在高空间分辨率和长序列情况下。我们提出DAGE，一种双流Transformer架构，其核心创新在于解耦全局一致性与细粒度细节。低分辨率流对大幅下采样后的帧使用交替帧/全局注意力，高效构建视图一致表征并估计相机位姿；高分辨率流逐帧处理原始图像以保留锐利边界和微小结构。一个轻量级适配器通过交叉注意力融合两路信息，注入全局上下文而不干扰预训练的单帧路径。该设计可独立扩展分辨率与片段长度，支持最高2K输入，且推理成本可控。DAGE生成清晰深度图/点云，具有强跨视角一致性与精确位姿，为视频几何估计与多视角重建树立新基准。
原文摘要 · Abstract (English)
Estimating accurate, view-consistent geometry and camera poses from uncalibrated multi-view/video inputs remains challenging - especially at high spatial resolutions and over long sequences. We present DAGE, a dual-stream transformer whose main novelty is to disentangle global coherence from fine detail. A low-resolution stream operates on aggressively downsampled frames with alternating frame/global attention to build a view-consistent representation and estimate cameras efficiently, while a high-resolution stream processes the original images per-frame to preserve sharp boundaries and small structures. A lightweight adapter fuses these streams via cross-attention, injecting global context without disturbing the pretrained single-frame pathway. This design scales resolution and clip length independently, supports inputs up to 2K, and maintains practical inference cost. DAGE delivers sharp depth/pointmaps, strong cross-view consistency, and accurate poses, establishing new state-of-the-art results for video geometry estimation and multi-view reconstruction.
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。