StereoFactory: A Unified Merging Framework for Robust Stereo Matching

• URL: http://arxiv.org/abs/2606.17475v1
• Date: Tue, 16 Jun 2026 03:36:59 GMT
• Title: StereoFactory: A Unified Merging Framework for Robust Stereo Matching
• Abstract summary: Stereo matching has advanced through foundation models trained on large-scale datasets, yet this paradigm suffers from a scalability bottleneck.<n>Model merging offers a scalable post-hoc alternative by integrating knowledge from specialized models after source checkpoints are available.<n>We propose StereoFactory, a coarse-to-fine evolutionary framework for adaptive model merging.
• Score: 61.973843344605655
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stereo matching has advanced through foundation models trained on large-scale datasets, yet this paradigm suffers from a scalability bottleneck: incorporating new data requires costly joint retraining. Model merging offers a scalable post-hoc alternative by integrating knowledge from specialized models after source checkpoints are available. However, existing merging methods typically retain all available models or rely on greedy inclusion, which can preserve harmful task-vector interference. We propose StereoFactory, a coarse-to-fine evolutionary framework for adaptive model merging. Stage~1 employs a genetic algorithm to search the combinatorial space of model subsets, determining which models should participate. Stage~2 addresses module-level knowledge specialization (different functional modules exhibit distinct preferences for knowledge sources) through CMA-ES optimization of architecture-adaptive routing over the selected task vectors, with optional module-level scaling. Experiments across two architectures and four benchmarks demonstrate that StereoFactory consistently achieves the best four-benchmark average under the same checkpoint pool, reducing the average error from 3.80 to 3.30 on NMRF and from 2.88 to 2.19 on FoundationStereo relative to the strongest controlled baseline. The post-hoc search requires only 2.7--3.7\% of the corresponding joint-retraining wall-clock time. Analysis reveals that knowledge contributions are inherently module-specific, and selected subsets can transfer across architectures with minimal degradation. Code will be publicly released upon acceptance at: https://github.com/XiandaGuo/StereoFactory.

Related papers

• A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition [1.547549252134621]
  We propose a unified backbone-expert framework with a common convolutional state-space backbone and two specialized interfaces.<n>Our framework achieves overall average accuracies of 67.28 pm 0.14% on RML2016.10b and 87.19 pm 0.77% on HisarMod 2019.
  arXiv  Detail & Related papers  (2026-08-15T10:26:42Z)
• Cross-device Collaborative Test-time Adaptation with Zeroth-order Optimization and Model Merging [26.385689556663724]
  Test-time adaptation (TTA) mitigates domain shifts by using incoming test data to update a model on the fly.<n>The majority of TTA methods require resource-intensive backpropagation (BP) for model updates.
  arXiv  Detail & Related papers  (2026-07-03T05:53:19Z)
• Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification [1.5269986601063288]
  This paper presents a configuration-first framework for evaluating cross-backend compatibility in deep learning systems.<n>The framework decouples experiments from code using YAML, supports both library and repository models, and employs a three-tier verification protocol.<n>We observe that 72.0% of runs pass, with most discrepancies occurring under stricter thresholds.
  arXiv  Detail & Related papers  (2025-08-29T16:28:28Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• PLeaS -- Merging Models with Permutations and Least Squares [43.17620198572947]
  We propose a new two-step algorithm to merge models -- termed PLeaS -- which relaxes constraints.<n>PLeaS partially matches nodes in each layer by maximizing alignment.<n>We also demonstrate how our method can be extended to address a challenging scenario where no data is available from the fine-tuning domains.
  arXiv  Detail & Related papers  (2024-07-02T17:24:04Z)
• Multi-Level Aggregation and Recursive Alignment Architecture for Efficient Parallel Inference Segmentation Network [18.47001817385548]
  We propose a parallel inference network customized for semantic segmentation tasks. We employ a shallow backbone to ensure real-time speed, and propose three core components to compensate for the reduced model capacity to improve accuracy. Our framework shows a better balance between speed and accuracy than state-of-the-art real-time methods on Cityscapes and CamVid datasets.
  arXiv  Detail & Related papers  (2024-02-03T22:51:17Z)
• 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)
• Squeezeformer: An Efficient Transformer for Automatic Speech Recognition [99.349598600887]
  Conformer is the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture. We propose the Squeezeformer model, which consistently outperforms the state-of-the-art ASR models under the same training schemes.
  arXiv  Detail & Related papers  (2022-06-02T06:06:29Z)
• Pack Together: Entity and Relation Extraction with Levitated Marker [61.232174424421025]
  We propose a novel span representation approach, named Packed Levitated Markers, to consider the dependencies between the spans (pairs) by strategically packing the markers in the encoder. Our experiments show that our model with packed levitated markers outperforms the sequence labeling model by 0.4%-1.9% F1 on three flat NER tasks, and beats the token concat model on six NER benchmarks.
  arXiv  Detail & Related papers  (2021-09-13T15:38:13Z)
• Adaptive Linear Span Network for Object Skeleton Detection [56.78705071830965]
  We propose adaptive linear span network (AdaLSN) to automatically configure and integrate scale-aware features for object skeleton detection. AdaLSN substantiates its versatility by achieving significantly higher accuracy and latency trade-off. It also demonstrates general applicability to image-to-mask tasks such as edge detection and road extraction.
  arXiv  Detail & Related papers  (2020-11-08T12:51:14Z)

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.