Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
132 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DCVSMNet: Double Cost Volume Stereo Matching Network (2402.16473v3)

Published 26 Feb 2024 in cs.CV

Abstract: We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost volumes. Each cost volume is processed separately, and a coupling module is proposed to fuse the geometry information extracted from the upper and lower cost volumes. DCVSMNet is a fast stereo matching network with a 67 ms inference time and strong generalization ability which can produce competitive results compared to state-of-the-art methods. The results on several bench mark datasets show that DCVSMNet achieves better accuracy than methods such as CGI-Stereo and BGNet at the cost of greater inference time.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Stereonet: Guided hierarchical refinement for real-time edge-aware depth prediction. In Proceedings of the European Conference on Computer Vision (ECCV), pages 573–590, 2018.
  2. Application of stereo-imaging technology to medical field. Healthcare informatics research, 18(3):158–163, 2012.
  3. Anytime stereo image depth estimation on mobile devices. In 2019 international conference on robotics and automation (ICRA), pages 5893–5900. IEEE, 2019.
  4. Fast cnn stereo depth estimation through embedded gpu devices. Sensors, 20(11):3249, 2020.
  5. A decomposition model for stereo matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6091–6100, 2021.
  6. Group-wise correlation stereo network. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3273–3282, 2019.
  7. Hierarchical neural architecture search for deep stereo matching. Advances in Neural Information Processing Systems, 33:22158–22169, 2020.
  8. Cfnet: Cascade and fused cost volume for robust stereo matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13906–13915, 2021.
  9. Aanet: Adaptive aggregation network for efficient stereo matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1959–1968, 2020.
  10. Hitnet: Hierarchical iterative tile refinement network for real-time stereo matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14362–14372, 2021.
  11. Practical stereo matching via cascaded recurrent network with adaptive correlation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16263–16272, 2022.
  12. Bilateral grid learning for stereo matching networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12497–12506, 2021.
  13. Multi-dimensional cooperative network for stereo matching. IEEE Robotics and Automation Letters, 7(1):581–587, 2021a.
  14. Accurate and efficient stereo matching via attention concatenation volume. arXiv preprint arXiv:2209.12699, 2022.
  15. Deeppruner: Learning efficient stereo matching via differentiable patchmatch. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4384–4393, 2019.
  16. Correlate-and-excite: Real-time stereo matching via guided cost volume excitation. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 3542–3548. IEEE, 2021.
  17. Multi-dimensional cooperative network for stereo matching. IEEE Robotics and Automation Letters, 7(1):581–587, 2021b.
  18. A joint 2d-3d complementary network for stereo matching. Sensors, 21(4):1430, 2021.
  19. Scv-stereo: Learning stereo matching from a sparse cost volume. In 2021 IEEE International Conference on Image Processing (ICIP), pages 3203–3207. IEEE, 2021a.
  20. Cgi-stereo: Accurate and real-time stereo matching via context and geometry interaction. arXiv preprint arXiv:2301.02789, 2023.
  21. Ga-net: Guided aggregation net for end-to-end stereo matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 185–194, 2019.
  22. Segstereo: Exploiting semantic information for disparity estimation. In Proceedings of the European conference on computer vision (ECCV), pages 636–651, 2018.
  23. Edgestereo: An effective multi-task learning network for stereo matching and edge detection. International Journal of Computer Vision, 128:910–930, 2020.
  24. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.
  25. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, pages 3354–3361. IEEE, 2012.
  26. Object scene flow for autonomous vehicles. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3061–3070, 2015.
  27. A multi-view stereo benchmark with high-resolution images and multi-camera videos. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3260–3269, 2017.
  28. High-resolution stereo datasets with subpixel-accurate ground truth. In Pattern Recognition: 36th German Conference, GCPR 2014, Münster, Germany, September 2-5, 2014, Proceedings 36, pages 31–42. Springer, 2014.
  29. A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4040–4048, 2016.
  30. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4):834–848, 2017.
  31. Optical flow estimation using a spatial pyramid network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4161–4170, 2017.
  32. Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8934–8943, 2018.
  33. Attention-aware feature aggregation for real-time stereo matching on edge devices. In Proceedings of the Asian Conference on Computer Vision, 2020.
  34. Real-time semantic stereo matching. In 2020 IEEE international conference on robotics and automation (ICRA), pages 10780–10787. IEEE, 2020.
  35. Semantic stereo matching with pyramid cost volumes. In Proceedings of the IEEE/CVF international conference on computer vision, pages 7484–7493, 2019.
  36. Learning efficient multi-task stereo matching network with richer feature information. Neurocomputing, 421:151–160, 2021b. ISSN 0925-2312. doi: https://doi.org/10.1016/j.neucom.2020.08.010. URL https://www.sciencedirect.com/science/article/pii/S0925231220312704.
  37. Multi-hierarchy feature extraction and multi-step cost aggregation for stereo matching. Neurocomputing, 492:601–611, 2022. ISSN 0925-2312. doi: https://doi.org/10.1016/j.neucom.2021.12.052. URL https://www.sciencedirect.com/science/article/pii/S0925231221018890.
  38. Adcpnet: Adaptive disparity candidates prediction network for efficient real-time stereo matching. arXiv preprint arXiv:2011.09023, 2020.
  39. Pyramid stereo matching network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5410–5418, 2018.
  40. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  41. Ebstereo: edge-based loss function for real-time stereo matching. The Visual Computer, pages 1–12, 2023.
  42. Learning depth with convolutional spatial propagation network. IEEE transactions on pattern analysis and machine intelligence, 42(10):2361–2379, 2019.
  43. Local similarity pattern and cost self-reassembling for deep stereo matching networks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 1647–1655, 2022a.
  44. Domain-invariant stereo matching networks. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, pages 420–439. Springer, 2020.
  45. Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6197–6206, 2021.
  46. Revisiting domain generalized stereo matching networks from a feature consistency perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13001–13011, 2022.
  47. Graftnet: Towards domain generalized stereo matching with a broad-spectrum and task-oriented feature. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13012–13021, 2022b.
  48. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520, 2018.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now