Scholarlink

<p>Stereo matching is a significant part in many computer vision tasks and driving-based applications. Recently cost volume-based methods have achieved great success benefiting from the rich geometry information in paired images. However, the redundancy of cost volume also interferes with the model training and limits the performance. To construct a more precise cost volume, we pioneeringly apply the diffusion model to stereo matching. Our method, termed DiffuVolume, considers the diffusion model as a cost volume filter, which will recurrently remove the redundant information from the cost volume. Two main designs make our method not trivial. Firstly, to make the diffusion model more adaptive to stereo matching, we eschew the traditional manner of directly adding noise into the image but embed the diffusion model into a task-specific module. In this way, we outperform the traditional diffusion stereo matching method by 27<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11263_2025_2362_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation> EPE improvement and 7 times parameters reduction. Secondly, DiffuVolume can be easily embedded into any volume-based stereo matching network, boosting performance with only a slight increase in parameters (approximately 2<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11263_2025_2362_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation>). By adding the DiffuVolume into well-performed methods, we outperform all the published methods on Scene Flow, KITTI2012, KITTI2015 benchmarks and zero-shot generalization setting. It is worth mentioning that the proposed model ranks 1<i>st</i> on KITTI 2012 leader board, 2<i>nd</i> on KITTI 2015 leader board since 15, July 2023.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DiffuVolume: Diffusion Model for Volume based Stereo Matching

  • 期刊论文

  • 发表日期：

    2025年2月1日

查看全文
  • Dian Zheng,
  • Xiao-Ming Wu,
  • Zuhao Liu,
  • Jingke Meng,
  • Wei-Shi Zheng

摘要

Stereo matching is a significant part in many computer vision tasks and driving-based applications. Recently cost volume-based methods have achieved great success benefiting from the rich geometry information in paired images. However, the redundancy of cost volume also interferes with the model training and limits the performance. To construct a more precise cost volume, we pioneeringly apply the diffusion model to stereo matching. Our method, termed DiffuVolume, considers the diffusion model as a cost volume filter, which will recurrently remove the redundant information from the cost volume. Two main designs make our method not trivial. Firstly, to make the diffusion model more adaptive to stereo matching, we eschew the traditional manner of directly adding noise into the image but embed the diffusion model into a task-specific module. In this way, we outperform the traditional diffusion stereo matching method by 27 \(\%\) % EPE improvement and 7 times parameters reduction. Secondly, DiffuVolume can be easily embedded into any volume-based stereo matching network, boosting performance with only a slight increase in parameters (approximately 2 \(\%\) % ). By adding the DiffuVolume into well-performed methods, we outperform all the published methods on Scene Flow, KITTI2012, KITTI2015 benchmarks and zero-shot generalization setting. It is worth mentioning that the proposed model ranks 1st on KITTI 2012 leader board, 2nd on KITTI 2015 leader board since 15, July 2023.