Saved in:
Bibliographic Details
Main Authors: Ngo, Tuan Duc, Huang, Jiahui, Oh, Seoung Wug, Blackburn-Matzen, Kevin, Kalogerakis, Evangelos, Gan, Chuang, Lee, Joon-Young
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.03744
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912977166270464
author Ngo, Tuan Duc
Huang, Jiahui
Oh, Seoung Wug
Blackburn-Matzen, Kevin
Kalogerakis, Evangelos
Gan, Chuang
Lee, Joon-Young
author_facet Ngo, Tuan Duc
Huang, Jiahui
Oh, Seoung Wug
Blackburn-Matzen, Kevin
Kalogerakis, Evangelos
Gan, Chuang
Lee, Joon-Young
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03744
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
Ngo, Tuan Duc
Huang, Jiahui
Oh, Seoung Wug
Blackburn-Matzen, Kevin
Kalogerakis, Evangelos
Gan, Chuang
Lee, Joon-Young
Computer Vision and Pattern Recognition
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.
title DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.03744