Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts

• URL: http://arxiv.org/abs/2507.04631v1
• Date: Mon, 07 Jul 2025 03:19:04 GMT
• Title: Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts
• Authors: Yun Wang, Longguang Wang, Chenghao Zhang, Yongjian Zhang, Zhanjie Zhang, Ao Ma, Chenyou Fan, Tin Lun Lam, Junjie Hu,
• Abstract summary: We propose SMoEStereo, a novel framework that adapts VFMs for stereo matching through a tailored, scene-specific fusion of Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE) modules.<n>Our method exhibits state-of-the-art cross-domain and joint generalization across multiple benchmarks without dataset-specific adaptation.
• Score: 29.52183168979229
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, learning-based stereo matching networks have advanced significantly. However, they often lack robustness and struggle to achieve impressive cross-domain performance due to domain shifts and imbalanced disparity distributions among diverse datasets. Leveraging Vision Foundation Models (VFMs) can intuitively enhance the model's robustness, but integrating such a model into stereo matching cost-effectively to fully realize their robustness remains a key challenge. To address this, we propose SMoEStereo, a novel framework that adapts VFMs for stereo matching through a tailored, scene-specific fusion of Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE) modules. SMoEStereo introduces MoE-LoRA with adaptive ranks and MoE-Adapter with adaptive kernel sizes. The former dynamically selects optimal experts within MoE to adapt varying scenes across domains, while the latter injects inductive bias into frozen VFMs to improve geometric feature extraction. Importantly, to mitigate computational overhead, we further propose a lightweight decision network that selectively activates MoE modules based on input complexity, balancing efficiency with accuracy. Extensive experiments demonstrate that our method exhibits state-of-the-art cross-domain and joint generalization across multiple benchmarks without dataset-specific adaptation. The code is available at \textcolor{red}{https://github.com/cocowy1/SMoE-Stereo}.

Related papers

• SAMamba: Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target Detection [12.964308630328688]
  Infrared small target detection (ISTD) is vital for long-range surveillance in military, maritime, and early warning applications.<n>ISTD is challenged by targets occupying less than 0.15% of the image and low distinguishability from complex backgrounds.<n>This paper presents SAMamba, a novel framework integrating SAM2's hierarchical feature learning with Mamba's selective sequence modeling.
  arXiv  Detail & Related papers  (2025-05-29T07:55:23Z)
• Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization [9.03028904066824]
  Open-set test-time adaptation (OSTTA) aims to adapt a source pre-trained model online to an unlabeled target domain that contains unknown classes.<n>We present Adaptive Entropy-aware Optimization (AEO), a novel framework specifically designed to tackle Multimodal Open-set Test-time Adaptation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:30Z)
• Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging [111.8456671452411]
  Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. We propose a Weight-Ensembling Mixture of Experts (WEMoE) method for multi-task model merging. We show that WEMoE and E-WEMoE outperform state-of-the-art (SOTA) model merging methods in terms of MTL performance, generalization, and robustness.
  arXiv  Detail & Related papers  (2024-10-29T07:16:31Z)
• Modality Prompts for Arbitrary Modality Salient Object Detection [57.610000247519196]
  This paper delves into the task of arbitrary modality salient object detection (AM SOD) It aims to detect salient objects from arbitrary modalities, eg RGB images, RGB-D images, and RGB-D-T images. A novel modality-adaptive Transformer (MAT) will be proposed to investigate two fundamental challenges of AM SOD.
  arXiv  Detail & Related papers  (2024-05-06T11:02:02Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching [77.133400999703]
  Correlation based stereo matching has achieved outstanding performance. Current methods with a fixed model do not work uniformly well across various datasets. This paper proposes a new perspective to dynamically calculate correlation for robust stereo matching.
  arXiv  Detail & Related papers  (2023-07-26T09:47:37Z)
• MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation [14.866949449862226]
  Vision Transformer (ViT) models are too computationally expensive to be fitted onto real-world resource-constrained devices. We propose a Multi-grained Input-adaptive Vision Transformer framework dubbed MIA-Former that can input-adaptively adjust the structure of ViTs. Experiments and ablation studies validate that the proposed MIA-Former framework can effectively allocate budgets adaptive to the difficulty of input images.
  arXiv  Detail & Related papers  (2021-12-21T22:06:24Z)
• AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach [50.855679274530615]
  We present a novel domain-adaptive approach called AdaStereo to align multi-level representations for deep stereo matching networks. Our models achieve state-of-the-art cross-domain performance on multiple benchmarks, including KITTI, Middlebury, ETH3D and DrivingStereo. Our method is robust to various domain adaptation settings, and can be easily integrated into quick adaptation application scenarios and real-world deployments.
  arXiv  Detail & Related papers  (2021-12-09T15:10:47Z)
• AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network [8.127449025802436]
  We present a novel recurrent multi-view stereo network based on long short-term memory (LSTM) with adaptive aggregation, namely AA-RMVSNet. We firstly introduce an intra-view aggregation module to adaptively extract image features by using context-aware convolution and multi-scale aggregation. We propose an inter-view cost volume aggregation module for adaptive pixel-wise view aggregation, which is able to preserve better-matched pairs among all views.
  arXiv  Detail & Related papers  (2021-08-09T06:10:48Z)
• Continual Adaptation for Deep Stereo [52.181067640300014]
  We propose a continual adaptation paradigm for deep stereo networks designed to deal with challenging and ever-changing environments. In our paradigm, the learning signals needed to continuously adapt models online can be sourced from self-supervision via right-to-left image warping or from traditional stereo algorithms. Our network architecture and adaptation algorithms realize the first real-time self-adaptive deep stereo system.
  arXiv  Detail & Related papers  (2020-07-10T08:15:58Z)

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.