• Home
  • Search
  • All-in-One: Transferring Vision Foundation Models into Stereo Matching
  • https://doi.org/10.1609/aaai.v39i10.33173Copy DOI Icon

All-in-One: Transferring Vision Foundation Models into Stereo Matching

  • Abstract
  • Literature Map
  • Similar Papers
Abstract

As a fundamental vision task, stereo matching has made remarkable progress. While recent iterative optimization-based methods have achieved promising performance, their feature extraction capabilities still have room for improvement. Inspired by the ability of vision foundation models (VFMs) to extract general representations, in this work, we propose AIO-Stereo which can flexibly select and transfer knowledge from multiple heterogeneous VFMs to a single stereo matching model. To better reconcile features between heterogeneous VFMs and the stereo matching model and fully exploit prior knowledge from VFMs, we proposed a dual-level feature utilization mechanism that aligns heterogeneous features and transfers multi-level knowledge. Based on the mechanism, a dual-level selective knowledge transfer module is designed to selectively transfer knowledge and integrate the advantages of multiple VFMs. Experimental results show that AIO-Stereo achieves start-of-the-art performance on multiple datasets and ranks 1st on the Middlebury dataset and outperforms all the published work on the ETH3D benchmark.

Similar Papers
  • Research Article
  • Citations200

A fast stereo matching algorithm suitable for embedded real-time systems

  • May 04, 2010
  • Computer Vision and Image Understanding
  • Martin Humenberger +4
  • Conference Article
  • Citations8

Stereo Matching Based on Visual Sensitive Information

  • Jul 23, 2021
  • Hewei Wang +2
  • PDF
  • Research Article
  • Citations1

Stereo Matching Based on Features of Image Patch

  • Jul 25, 2021
  • Journal of the Institute of Industrial Applications Engineers
  • Shi Zhou +5
  • Book Chapter
  • Citations2

Real-Time Stereo Matching System

  • Jan 01, 2018
  • Angfan Zhu +2
  • Research Article
  • Citations2

Thermal-visible stereo matching at night based on Multi-Modal Autoencoder

  • Dec 07, 2023
  • Infrared Physics & Technology
  • Quan Zhang +6
  • Research Article

Context Geometry Volume and Warping Refinement for Real-Time Stereo Matching

  • Feb 24, 2025
  • Electronics
  • Ning Liu +4
  • Conference Article

An Improved Stereo Matching Network Based on Modified PSMNet

  • Dec 09, 2022
  • Hua Shen +5
  • Research Article

Multi-attention Ghost Pyramid Fusion Network for Script Identification of Chinese Ancient Document Images

  • Sep 08, 2025
  • ACM Transactions on Asian and Low-Resource Language Information Processing
  • Hai Guo +3
  • Research Article
  • Citations13

Outlier detection and disparity refinement in stereo matching

  • Mar 09, 2019
  • Journal of Visual Communication and Image Representation
  • Qicong Dong +1
  • PDF
  • Research Article
  • Citations11

Edge-Preserving Stereo Matching Using Minimum Spanning Tree

  • Jan 01, 2019
  • IEEE Access
  • Congxuan Zhang +5
  • Book Chapter
  • Citations21

A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching

  • Jan 01, 2012
  • Shengqi Zhu +2
  • Research Article
  • Citations20

Stereo matching using weighted dynamic programming on a single-direction four-connected tree

  • Apr 25, 2012
  • Computer Vision and Image Understanding
  • Tingbo Hu +4
  • Book Chapter

Hierarchical Stereo Matching Based on Image Bit-Plane Slicing

  • Jan 01, 2013
  • Huei-Yung Lin +1
  • Conference Article

On-device stereo matching using NPU acceleration for real-time depth estimation

  • Feb 27, 2026
  • Mingi Park +1
  • Conference Article

Research on Intelligent Signal Processing System in Optoelectronic Technology

  • Apr 25, 2025
  • Jing Lü +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.