Skip to main content

Advertisement

Springer Nature Link
Log in

Sliding space-disparity transformer for stereo matching

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Transformers have achieved impressive performance in natural language processing and computer vision, including text translation, semantic segmentation, etc. However, due to excessive self-attention computation and memory occupation, the stereo matching task does not share its success. To promote this technology in stereo matching, especially with limited hardware resources, we propose a sliding space-disparity transformer named SSD-former. According to matching modeling, we simplify transformer for achieving faster speed, memory-friendly, and competitive performance. First, we employ the sliding window scheme to limit the self-attention operations in the cost volume for adapting to different resolutions, bringing efficiency and flexibility. Second, our space-disparity transformer remarkably reduces memory occupation and computation, only computing the current patch’s self-attention with two parts: (1) all patches of current disparity level at the whole spatial location and (2) the patches of different disparity levels at the exact spatial location. The experiments demonstrate that: (1) different from the standard transformer, SSD-former is faster and memory-friendly; (2) compared with 3D convolution methods, SSD-former has a larger receptive field and provides an impressive speed, showing great potential in stereo matching; and (3) our model obtains state-of-the-art performance and a faster speed on the multiple popular datasets, achieving the best speed–accuracy trade-off.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. https://github.com/RaoHaocheng/SSD-former.

  2. http://www.cvlibs.net/datasets/kitti/.

  3. https://www.eth3d.net/low_res_two_view.

References

  1. Beltagy I, Peters ME, Cohan A (2020) Longformer: The long-document transformer. In: arXiv preprint arXiv:2004.05150

  2. Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A et al. (2020) Language models are few-shot learners. In: arXiv preprint arXiv:2005.14165

  3. Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision (ECCV), pp. 213–229

  4. Chang JR, Chen YS (2018) Pyramid stereo matching network. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 5410–5418

  5. Chen Y, Kalantidis Y, Li J, Yan S, Feng J (2018) Multi-fiber networks for video recognition. In: European conference on computer vision (ECCV), pp. 352–367

  6. Cheng X, Zhong Y, Harandi M, Dai Y, Chang X, Li H, Drummond T, Ge Z (2020) Hierarchical neural architecture search for deep stereo matching. In: Advances in Neural Information Processing Systems (NIPS), Vol 33. pp 22158–22169

  7. Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 10578–10587

  8. Dai Y, Zhu Z, Rao Z, Li B (2019) Mvs\(^2\): Deep unsupervised multi-view stereo with multi-view symmetry. In: International Conference on 3d vision (3DV), pp. 1–8

  9. Dai Z, Yang Z, Yang Y, Carbonell J, Le QV, Salakhutdinov R (2019) Transformer-xl: Attentive language models beyond a fixed-length context. In: arXiv preprint arXiv:1901.02860

  10. Di Gangi MA, Negri M, Cattoni R, Roberto D, Turchi M (2019) Enhancing transformer for end-to-end speech-to-text translation. In: Machine Translation Summit XVII, pp. 21–31

  11. Ding Y, Hua L, Li S (2021) Research on computer vision enhancement in intelligent robot based on machine learning and deep learning. Neural Comput Appl 34:2623–2635

    Article  Google Scholar 

  12. Ding Y, Lin L, Wang L, Zhang M, Li D (2020) Digging into the multi-scale structure for a more refined depth map and 3d reconstruction. Neural Comput Appl 32:11217–11228

    Article  Google Scholar 

  13. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al. (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: arXiv preprintarXiv:2010.11929

  14. Duggal S, Wang S, Ma WC, Hu R, Urtasun R (2019) Deeppruner: Learning efficient stereo matching via differentiable patchmatch. In: IEEE International Conference on computer vision (ICCV), pp. 4384–4393

  15. Fang X (2021) Making recommendations using transfer learning. Neural Comput Appl 33:9663–9676

    Article  Google Scholar 

  16. Fang Y, Ma Z, Zheng H, Ji W (2020) Trainable tv-\(l_1\) model as recurrent nets for low-level vision. Neural Comput Appl 32(18):14603-14611

    Article  Google Scholar 

  17. Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 3354–3361

  18. Guo X, Yang K, Yang W, Wang X, Li H (2019) Group-wise correlation stereo network. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 3273–3282

  19. Hirschmuller H (2007) Stereo processing by semiglobal matching and mutual information. IEEE Trans Pattern Anal Mach Intell. 30(2):328–341

    Article  Google Scholar 

  20. Hu B, Zhang Z (2021) Bio-inspired visual neural network on spatio-temporal depth rotation perception. Neural Comput Appl 33:10351–10370

    Article  Google Scholar 

  21. Joshi M, Chen D, Liu Y, Weld DS, Zettlemoyer L, Levy O (2020) Spanbert: Improving pre-training by representing and predicting spans. Transactions of the association for computational linguistics 8:64–77

  22. Kendall A, Martirosyan H, Dasgupta S, Henry P, Kennedy R, Bachrach A, Bry A (2017) End-to-end learning of geometry and context for deep stereo regression. In: IEEE International Conference on computer vision (ICCV), pp. 66–75

  23. Kim TH, Sajjadi MS, Hirsch M, Scholkopf B (2018) Spatio-temporal transformer network for video restoration. In: European Conference on computer vision (ECCV), pp. 106–122

  24. Li D, Deng L, Cai Z (2020) Design of traffic object recognition system based on machine learning. Neural Comput Appl 33:8143–8156

    Article  Google Scholar 

  25. Li X, Fan Y, Rao Z, Lv G, Liu S (2021) Synthetic-to-real domain adaptation joint spatial feature transform for stereo matching. IEEE Signal Process Lett 29:60–64

    Article  Google Scholar 

  26. Li X, Hou Y, Wang P, Gao Z, Xu M, Li W (2021) Transformer guided geometry model for flow-based unsupervised visual odometry. Neural Comput Appl 33:8031-8042

    Article  Google Scholar 

  27. Li Z, Liu X, Drenkow N, Ding A, Creighton FX, Taylor RH, Unberath M (2021) Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. IEEE International Conference on computer vision and pattern recognition (CVPR) pp. 6197–6206

  28. Liang J, Homayounfar N, Ma WC, Xiong Y, Hu R, Urtasun R (2020) Polytransform: Deep polygon transformer for instance segmentation. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 9131–9140

  29. Liu H, Lu J, Feng J, Zhou J (2017) Two-stream transformer networks for video-based face alignment. IEEE Trans Pattern Anal Mach Intell 40(11):2546–2554

    Article  Google Scholar 

  30. Mayer N, Ilg E, Häusser P, Fischer P, Cremers D, Dosovitskiy A, Brox T (2016) A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 4040–4048

  31. Menze M, Geiger A (2015) Object scene flow for autonomous vehicles. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 3061–3070

  32. Potamias RA, Siolas G, Stafylopatis AG (2020) A transformer-based approach to irony and sarcasm detection. Neural Comput Appl 32(23):17309–17320

    Article  Google Scholar 

  33. Rao Z, Dai Y, Shen Z, He R (2022) Rethinking training strategy in stereo matching. IEEE Trans Neural Networks Learn Syst. https://doi.org/10.1109/TNNLS.2022.3146306

    Article  Google Scholar 

  34. Rao Z, He M, Dai Y, Shen Z (2022) Patch attention network with generative adversarial model for semi-supervised binocular disparity prediction. Visual Comput 38:77–93

    Article  Google Scholar 

  35. Rao Z, He M, Dai Y, Zhu Z, Li B, He R (2020) Nlca-net: a non-local context attention network for stereo matching. APSIPA Trans Signal Inf Process 9:e1–e13

    Article  Google Scholar 

  36. Rao Z, He M, Zhu Z, Dai Y, He R (2021) Bidirectional guided attention network for 3-d semantic detection of remote sensing images. IEEE Trans Geosci Remote Sens 59(7):6138–6153

    Article  Google Scholar 

  37. Schops T, Schonberger JL, Galliani S, Sattler T, Schindler K, Pollefeys M, Geiger A (2017) A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 3260–3269

  38. Seki A, Pollefeys M (2017) Sgm-nets: Semi-global matching with neural networks. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 6640–6649

  39. So D, Le Q, Liang C (2019) The evolved transformer. In: International Conference on machine learning, pp. 5877–5886

  40. Tankovich V, Häne C, Fanello S, Zhang Y, Izadi S, Bouaziz S (2020) Hitnet: Hierarchical iterative tile refinement network for real-time stereo matching. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 14362–14372

  41. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems (NIPS), pp. 5998–6008

  42. Wu Z, Wu X, Zhang X, Wang S, Ju L (2019) Semantic stereo matching with pyramid cost volumes. In: IEEE International Conference on computer vision (ICCV), pp. 7484–7493

  43. Xu H, Zhang J (2020) Aanet: Adaptive aggregation network for efficient stereo matching. In: IEEE International Conference on computer vision and pattern recognition (CVPR),1959–1968

  44. Yang F, Yang H, Fu J, Lu H, Guo B (2020) Learning texture transformer network for image super-resolution. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 5791–5800

  45. Yang G, Manela J, Happold M, Ramanan D (2019) Hierarchical deep stereo matching on high-resolution images. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 5515–5524

  46. Yin Z, Darrell T, Yu F (2019) Hierarchical discrete distribution decomposition for match density estimation. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 6044–6053

  47. Zbontar J, LeCun Y et al (2016) Stereo matching by training a convolutional neural network to compare image patches. J Mach Learn Res 17(1):2287–2318

    MATH  Google Scholar 

  48. Zhai M, Xiang X (2021) Geometry understanding from autonomous driving scenarios based on feature refinement. Neural Comput Appl 33(8):3209–3220

    Article  Google Scholar 

  49. Zhang F, Prisacariu V, Yang R, Torr PH (2019) Ga-net: Guided aggregation net for end-to-end stereo matching. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 185–194

  50. Zhang F, Qi X, Yang R, Prisacariu V, Wah B, Torr P (2020) Domain-invariant stereo matching networks. In: European Conference on computer vision (ECCV), pp. 420–439

  51. Zhang Y, Chen Y, Bai X, Yu S, Yu K, Li Z, Yang K (2020) Adaptive unimodal cost volume filtering for deep stereo matching. In: the Association for the advance of artificial intelligence (AAAI), vol. 34, pp. 12926–12934

  52. Zhang Z, Wu Y, Zhou J, Duan S, Zhao H, Wang R (2020) Sg-net: Syntax-guided machine reading comprehension. In: the Association for the advance of artificial intelligence (AAAI), vol. 34, pp. 9636–9643

  53. Zheng S, Lu J, Zhao H, Zhu X, Luo Z, Wang Y, Fu Y, Feng J, Xiang T, Torr PH et al. (2020) Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: IEEE International Conference on computer vision and pattern recognition (CVPR), pp. 6881–6890

  54. Zhong Y, Dai Y, Li H (2017) Self-supervised learning for stereo matching with self-improving ability. In: arXiv preprint arXiv:1709.00930

Download references

Acknowledgements

This work was supported in part by National Natural Science Foundation of China (61671387, 61420106007, 61871325, and 62001396).

Author information

Authors and Affiliations

  1. Northwestern Polytechnical University, Xi’an, 710129, China

    Zhibo Rao, Mingyi He & Yuchao Dai

  2. Baidu Research, Beijing, 100193, China

    Zhelun Shen

Authors
  1. Zhibo Rao
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mingyi He
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yuchao Dai
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Zhelun Shen
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mingyi He.

Ethics declarations

Conflicts of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rao, Z., He, M., Dai, Y. et al. Sliding space-disparity transformer for stereo matching. Neural Comput & Applic 34, 21863–21876 (2022). https://doi.org/10.1007/s00521-022-07621-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07621-7

Keywords