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.
@article{arxiv.2603.03744,
title = {DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation},
author = {Tuan Duc Ngo and Jiahui Huang and Seoung Wug Oh and Kevin Blackburn-Matzen and Evangelos Kalogerakis and Chuang Gan and Joon-Young Lee},
journal= {arXiv preprint arXiv:2603.03744},
year = {2026}
}