MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement

• URL: http://arxiv.org/abs/2604.20393v1
• Date: Wed, 22 Apr 2026 09:56:36 GMT
• Title: MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement
• Abstract summary: ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability.<n>The ability of ViT-based methods to predict details and handle arbitrary-resolution images is still weaker than that of CNN-based methods.<n>We propose MLG-Stereo, a systematic pipeline-level design that extends global modeling beyond the encoder stage.
• Score: 26.707660992617633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to the limitations of ViTs in handling resolution sensitivity and their relative neglect of local information, the ability of ViT-based methods to predict details and handle arbitrary-resolution images is still weaker than that of CNN-based methods. To address these shortcomings, we propose MLG-Stereo, a systematic pipeline-level design that extends global modeling beyond the encoder stage. First, we propose a Multi-Granularity Feature Network to effectively balance global context and local geometric information, enabling comprehensive feature extraction from images of arbitrary resolution and bridging the gap between training and inference scales. Then, a Local-Global Cost Volume is constructed to capture both locally-correlated and global-aware matching information. Finally, a Local-Global Guided Recurrent Unit is introduced to iteratively optimize the disparity locally under the guidance of global information. Extensive experiments are conducted on multiple benchmark datasets, demonstrating that our MLG-Stereo exhibits highly competitive performance on the Middlebury and KITTI-2015 benchmarks compared to contemporaneous leading methods, and achieves outstanding results in the KITTI-2012 dataset.

Related papers

• UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction [83.48950950780554]
  Building extraction from remote sensing images is a challenging task due to the complex structure variations of buildings.<n>Existing methods employ convolutional or self-attention blocks to capture the multi-scale features in the segmentation models.<n>We present an Uncertainty-Aggregated Global-Local Fusion Network (UAGLNet) to exploit high-quality global-local visual semantics.
  arXiv  Detail & Related papers  (2025-12-15T02:59:16Z)
• Scale-DiT: Ultra-High-Resolution Image Generation with Hierarchical Local Attention [50.391914489898774]
  Scale-DiT is a new diffusion framework that introduces hierarchical local attention with low-resolution global guidance.<n>A lightweight LoRA adaptation bridges global and local pathways during denoising, ensuring consistency across structure and detail.<n>Experiments demonstrate that Scale-DiT achieves more than $2times$ faster inference and lower memory usage.
  arXiv  Detail & Related papers  (2025-10-18T03:15:26Z)
• Glocal Information Bottleneck for Time Series Imputation [70.41814118117311]
  Time Series Imputation aims to recover missing values in temporal data.<n>Existing models typically optimize the point-wise reconstruction loss, focusing on recovering numerical values (local information)<n>We propose a new training paradigm, Glocal Information Bottleneck (Glocal-IB)
  arXiv  Detail & Related papers  (2025-10-06T15:24:44Z)
• Global Regulation and Excitation via Attention Tuning for Stereo Matching [21.40608901253552]
  We propose the Global Regulation and Excitation via Attention Tuning (GREAT) framework which encompasses three attention modules.<n>Specifically, Spatial Attention (SA) captures the global context within the spatial dimension, Matching Attention (MA) extracts global context along epipolar lines, and Volume Attention (VA) works in conjunction with SA and MA to construct a more robust cost-volume excited by global context and geometric details.<n>This framework demonstrates superior performance in challenging ill-posed regions.
  arXiv  Detail & Related papers  (2025-09-19T11:42:07Z)
• DSFormer: A Dual-Scale Cross-Learning Transformer for Visual Place Recognition [16.386674597850778]
  We propose a novel framework that integrates Dual-Scale-Former (DSFormer), a Transformer-based cross-learning module, with an innovative block clustering strategy.<n>Our approach achieves state-of-the-art performance across most benchmark datasets.
  arXiv  Detail & Related papers  (2025-07-24T14:29:30Z)
• MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection [12.838872442435527]
  Small object detection in UAV imagery is crucial for applications such as search-and-rescue, traffic monitoring, and environmental surveillance.<n>Existing multi-scale fusion methods help, but add computational burden and blur fine details.<n>We propose a unified fusion framework that tightly couples global context with local detail to boost detection performance.
  arXiv  Detail & Related papers  (2025-06-15T02:54:25Z)
• Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities [49.835556586263834]
  We propose a Global-Local Distillation-based Tracker (GLDTracker) for robust audio-visual speaker tracking.<n>GLDTracker is driven by a teacher-student distillation model, enabling the flexible fusion of incomplete information from each modality.<n> Experimental results on the AV16.3 dataset demonstrate that the proposed GLDTracker outperforms existing state-of-the-art audio-visual trackers.
  arXiv  Detail & Related papers  (2024-08-26T19:09:21Z)
• Recognize Any Regions [55.76437190434433]
  RegionSpot integrates position-aware localization knowledge from a localization foundation model with semantic information from a ViL model.<n>Experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives.
  arXiv  Detail & Related papers  (2023-11-02T16:31:49Z)
• RING++: Roto-translation Invariant Gram for Global Localization on a Sparse Scan Map [20.276334172402763]
  We propose RING++ which has roto-translation invariant representation for place recognition, and global convergence for both rotation and translation estimation. With the theoretical guarantee, RING++ is able to address the large viewpoint difference using a lightweight map with sparse scans. This is the first learning-free framework to address all subtasks of global localization in the sparse scan map.
  arXiv  Detail & Related papers  (2022-10-12T07:49:24Z)
• An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning [77.72330187258498]
  We propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet) ERPCNet extracts and aggregates localities based on semantic relevance and visual correlations without human-annotated regions. It not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization.
  arXiv  Detail & Related papers  (2021-11-03T11:13:13Z)
• Crowd Counting via Hierarchical Scale Recalibration Network [61.09833400167511]
  We propose a novel Hierarchical Scale Recalibration Network (HSRNet) to tackle the task of crowd counting. HSRNet models rich contextual dependencies and recalibrating multiple scale-associated information. Our approach can ignore various noises selectively and focus on appropriate crowd scales automatically.
  arXiv  Detail & Related papers  (2020-03-07T10:06:47Z)

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.