DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation

• URL: http://arxiv.org/abs/2603.03744v1
• Date: Wed, 04 Mar 2026 05:29:29 GMT
• Title: DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation
• Abstract summary: DAGE is a dual-stream transformer that disentangles global coherence from fine detail.<n>A low-resolution stream operates on aggressively downsampled frames with alternating frame/global attention to build a view-consistent representation.<n>A high-resolution stream processes the original images per-frame to preserve sharp boundaries and small structures.<n>This design scales resolution and clip length independently, supports inputs up to 2K, and maintains practical inference cost.
• Score: 72.89376712495464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry [31.83986431141471]
  We propose Feedforward Visual Odometry (FFVO), a pose-specialized adaptation of joint reconstruction architectures for efficient and temporally stable camera-pose estimation.<n>FFVO uses (i) a compact camera-token representation for computationally efficient temporal aggregation, (ii) a hierarchical local-to-global temporal decoder, and (iii) intermediate trajectory supervision that promotes temporal stability.
  arXiv  Detail & Related papers  (2026-09-12T05:56:52Z)
• OmniPoint: Universal Monocular Metric Pointcloud from Any Camera [79.24417597712802]
  We present OmniPoint, a unified framework designed to generalize metric reconstruction across diverse imaging sensors.<n>To overcome projection rigidity, OmniPoint abandons conventional planar depth regression.<n>It instead adopts a decoupled ray and distance representation alongside a decoupled training objective.
  arXiv  Detail & Related papers  (2026-09-08T19:45:58Z)
• CasDeblurGS: Cascaded 2D-to-3D Multi-View Consistency for 3D Gaussian Splatting from Two Blurry Images [2.12833538322985]
  Free-viewpoint 3D scene media is increasingly important for immersive applications, but practical capture often suffers from view sparsity and motion blur.<n>We propose CasDeblurGS, a cascaded framework that progressively recovers reliable cross-view information from local 2D correspondences to global 3D guidance.<n> Experiments on real-world and synthetic Deblur-NeRF scenes show consistent gains over strong baselines, improving PSNR by 1.19 dB and 2.11 dB, respectively.
  arXiv  Detail & Related papers  (2026-08-11T01:13:21Z)
• Sphere-VIO: Fast and Robust Visual-Inertial Odometry via Unified Spherical Representation for Heterogeneous Multi-Camera Systems [11.777651307702174]
  Multi-camera visual-inertial odometry (VIO) overcomes the inherent limitations of pure visual systems by expanding the field of view.<n>We present Sphere-VIO, a lightweight filter-based VIO framework with unified spherical representation for heterogeneous multi-camera systems.<n>We show that Sphere-VIO achieves superior trade-offs between accuracy, robustness, efficiency, and cross-camera generality.
  arXiv  Detail & Related papers  (2026-06-29T07:46:08Z)
• CalibAnyView: Beyond Single-View Camera Calibration in the Wild [59.66873936532375]
  Camera calibration is a fundamental prerequisite for reliable geometric perception.<n>Recent learning-based methods have shown promising results for single-view calibration, but inherently neglect geometric consistency across multiple views.<n>We introduce CalibAnyView, a unified formulation that supports an arbitrary number of input views.
  arXiv  Detail & Related papers  (2026-05-14T09:32:12Z)
• Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors [61.34273238077091]
  We present a novel method for generating orbital videos from a single image of an object.<n>Our method achieves superior visual quality, shape realism and multi-view consistency compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-14T05:35:46Z)
• ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors [48.033666517340464]
  ScrollScape is a novel framework that reformulates EAR image synthesis into a continuous video generation process.<n>We show that ScrollScape significantly outperforms existing image-diffusion baselines by eliminating severe localized artifacts.
  arXiv  Detail & Related papers  (2026-03-25T13:03:02Z)
• UCM: Unifying Camera Control and Memory with Time-aware Positional Encoding Warping for World Models [54.564740558030245]
  We present UCM, a novel framework that unifies long-term memory and precise camera control via a time-aware positional encoding warping mechanism.<n>We also introduce a scalable data curation strategy utilizing point-cloud-based rendering to simulate scene revisiting.
  arXiv  Detail & Related papers  (2026-02-26T12:54:46Z)
• StableDPT: Temporal Stable Monocular Video Depth Estimation [14.453483279783908]
  We propose a novel approach that adapts any state-of-the-art image-based (depth) estimation model for video processing.<n>Our architecture builds upon an off-the-shelf Vision Transformer (ViT) encoder and enhances the Dense Prediction Transformer (DPT) head.<n> Evaluations on multiple benchmark datasets demonstrate improved temporal consistency, competitive state-of-the-art performance and on top 2x faster processing in real-world scenarios.
  arXiv  Detail & Related papers  (2026-01-06T08:02:14Z)
• Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer [40.778996326009185]
  We present the first visual localization framework that performs multi-view spatial integration through an early-fusion mechanism.<n>Our framework is built upon the VGGT backbone, which encodes multi-view 3D geometry.<n>We propose a novel sparse mask attention strategy that reduces computational cost by avoiding the quadratic complexity of global attention.
  arXiv  Detail & Related papers  (2025-12-26T06:12:17Z)
• TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction [57.46712611558817]
  3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass.<n>Recent strategies align consecutive predictions by solving global transformation, yet our analysis reveals their fundamental limitations in assumption validity, local alignment scope, and robustness under noisy geometry.<n>We propose a higher-DOF and long-term alignment framework based on Thin Plate Spline, leveraging globally propagated control points to correct spatially varying inconsistencies.
  arXiv  Detail & Related papers  (2025-12-02T02:22:20Z)
• End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer [7.19764062839405]
  We present a fully end-to-end framework for multi-person 2D pose estimation in videos.<n>A key challenge is to associate individuals across frames under complex and overlapping temporal trajectories.<n>We introduce a novel Pose-Aware VideoErEr Network (PAVE-Net), which features a spatial encoder to model intra-frame relations and atemporal decoder pose.
  arXiv  Detail & Related papers  (2025-11-17T10:19:35Z)
• Visual Odometry with Transformers [68.453547770334]
  We introduce Visual odometry Transformer (VoT), which processes sequences of monocular frames by extracting features.<n>Unlike prior methods, VoT directly predicts camera motion without estimating dense geometry and relies solely on camera poses for supervision.<n>VoT scales effectively with larger datasets, benefits substantially from stronger pre-trained backbones, generalizes across diverse camera motions and calibration settings, and outperforms traditional methods while running more than 3 times faster.
  arXiv  Detail & Related papers  (2025-10-02T17:00:14Z)
• Pixel-Aligned Multi-View Generation with Depth Guided Decoder [86.1813201212539]
  We propose a novel method for pixel-level image-to-multi-view generation. Unlike prior work, we incorporate attention layers across multi-view images in the VAE decoder of a latent video diffusion model. Our model enables better pixel alignment across multi-view images.
  arXiv  Detail & Related papers  (2024-08-26T04:56:41Z)
• Continuous Space-Time Video Super-Resolution Utilizing Long-Range Temporal Information [48.20843501171717]
  We propose a continuous ST-VSR (CSTVSR) method that can convert the given video to any frame rate and spatial resolution. We show that the proposed algorithm has good flexibility and achieves better performance on various datasets.
  arXiv  Detail & Related papers  (2023-02-26T08:02:39Z)
• Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo [71.59494156155309]
  Existing approaches for multi-view 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views. We present our multi-view 3D pose estimation approach based on plane sweep stereo to jointly address the cross-view fusion and 3D pose reconstruction in a single shot.
  arXiv  Detail & Related papers  (2021-04-06T03:49:35Z)
• DFVS: Deep Flow Guided Scene Agnostic Image Based Visual Servoing [11.000164408890635]
  Existing deep learning based visual servoing approaches regress the relative camera pose between a pair of images. We consider optical flow as our visual features, which are predicted using a deep neural network. We show convergence for over 3m and 40 degrees while maintaining precise positioning of under 2cm and 1 degree.
  arXiv  Detail & Related papers  (2020-03-08T11:42:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.