Saved in:
Bibliographic Details
Main Author: Shi, Yuguang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.09051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916204893962240
author Shi, Yuguang
author_facet Shi, Yuguang
contents Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of detail that can be expressed in the generated disparity map. In order to address these issues, we propose a novel training approach that incorporates diffusion models into the iterative optimization process. We designed a Time-based Gated Recurrent Unit (T-GRU) to correlate temporal and disparity outputs. Unlike standard recurrent units, we employ Agent Attention to generate more expressive features. We also designed an attention-based context network to capture a large amount of contextual information. Experiments on several public benchmarks show that we have achieved competitive stereo matching performance. Our model ranks first in the Scene Flow dataset, achieving over a 7% improvement compared to competing methods, and requires only 8 iterations to achieve state-of-the-art results.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09051
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective
Shi, Yuguang
Computer Vision and Pattern Recognition
Artificial Intelligence
Recently, iteration-based stereo matching has shown great potential. However, these models optimize the disparity map using RNN variants. The discrete optimization process poses a challenge of information loss, which restricts the level of detail that can be expressed in the generated disparity map. In order to address these issues, we propose a novel training approach that incorporates diffusion models into the iterative optimization process. We designed a Time-based Gated Recurrent Unit (T-GRU) to correlate temporal and disparity outputs. Unlike standard recurrent units, we employ Agent Attention to generate more expressive features. We also designed an attention-based context network to capture a large amount of contextual information. Experiments on several public benchmarks show that we have achieved competitive stereo matching performance. Our model ranks first in the Scene Flow dataset, achieving over a 7% improvement compared to competing methods, and requires only 8 iterations to achieve state-of-the-art results.
title Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspective
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.09051