UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching

• URL: http://arxiv.org/abs/2409.02545v1
• Date: Wed, 4 Sep 2024 09:02:01 GMT
• Title: UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
• Authors: Soomin Kim, Hyesong Choi, Jihye Ahn, Dongbo Min,
• Abstract summary: UniTT-Stereo is a method to maximize the potential of Transformer-based stereo architectures. State-of-the-art performance of UniTT-Stereo is validated on various benchmarks such as ETH3D, KITTI 2012, and KITTI 2015 datasets.
• Score: 18.02254687807291
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unlike other vision tasks where Transformer-based approaches are becoming increasingly common, stereo depth estimation is still dominated by convolution-based approaches. This is mainly due to the limited availability of real-world ground truth for stereo matching, which is a limiting factor in improving the performance of Transformer-based stereo approaches. In this paper, we propose UniTT-Stereo, a method to maximize the potential of Transformer-based stereo architectures by unifying self-supervised learning used for pre-training with stereo matching framework based on supervised learning. To be specific, we explore the effectiveness of reconstructing features of masked portions in an input image and at the same time predicting corresponding points in another image from the perspective of locality inductive bias, which is crucial in training models with limited training data. Moreover, to address these challenging tasks of reconstruction-and-prediction, we present a new strategy to vary a masking ratio when training the stereo model with stereo-tailored losses. State-of-the-art performance of UniTT-Stereo is validated on various benchmarks such as ETH3D, KITTI 2012, and KITTI 2015 datasets. Lastly, to investigate the advantages of the proposed approach, we provide a frequency analysis of feature maps and the analysis of locality inductive bias based on attention maps.

Related papers

• MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling [18.02254687807291]
  Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data scarcity issue in the stereo matching task. We propose Masked Image Modeling Distilled Stereo matching model, termed MaDis-Stereo, that enhances locality inductive bias by leveraging Masked Image Modeling (MIM) in training Transformer-based stereo model.
  arXiv  Detail & Related papers  (2024-09-04T16:17:45Z)
• Rethinking the Key Factors for the Generalization of Remote Sensing Stereo Matching Networks [15.456986824737067]
  Stereo matching task relies on expensive airborne LiDAR data. In this paper, we study key training factors from three perspectives. We present an unsupervised stereo matching network with good generalization performance.
  arXiv  Detail & Related papers  (2024-08-14T15:26:10Z)
• Stereo Risk: A Continuous Modeling Approach to Stereo Matching [110.22344879336043]
  We introduce Stereo Risk, a new deep-learning approach to solve the classical stereo-matching problem in computer vision. We demonstrate that Stereo Risk enhances stereo-matching performance for deep networks, particularly for disparities with multi-modal probability distributions. A comprehensive analysis demonstrates our method's theoretical soundness and superior performance over the state-of-the-art methods across various benchmark datasets.
  arXiv  Detail & Related papers  (2024-07-03T14:30:47Z)
• 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)
• PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation [67.41325356479229]
  We propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix. In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient. This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner.
  arXiv  Detail & Related papers  (2022-07-27T07:48:29Z)
• 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)
• Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead [88.17413955380262]
  We introduce a novel architecture for early exiting based on the vision transformer architecture. We show that our method works for both classification and regression problems. We also introduce a novel method for integrating audio and visual modalities within early exits in audiovisual data analysis.
  arXiv  Detail & Related papers  (2021-05-19T13:30:34Z)
• PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching [14.603116313499648]
  We propose a robust and effective self-supervised stereo matching approach, consisting of a pyramid voting module (PVM) and a novel DCNN architecture, referred to as OptStereo. Specifically, our OptStereo first builds multi-scale cost volumes, and then adopts a recurrent unit to iteratively update disparity estimations at high resolution. We publish the HKUST-Drive dataset, a large-scale synthetic stereo dataset, collected under different illumination and weather conditions for research purposes.
  arXiv  Detail & Related papers  (2021-03-12T05:27:14Z)
• AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching [50.06646151004375]
  A novel domain-adaptive pipeline called AdaStereo aims to align multi-level representations for deep stereo matching networks. Our AdaStereo models achieve state-of-the-art cross-domain performance on multiple stereo benchmarks, including KITTI, Middlebury, ETH3D, and DrivingStereo.
  arXiv  Detail & Related papers  (2020-04-09T16:15:13Z)

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.