Abstract
In this paper, we propose a video-besed method for self-supervised human depth estimation, aiming at the problem of joint point distortion in human depth and insufficient utilization of 3D information in video-based depth estimation. We use the relative ordinal relations between human joint point pairs to deal with the problem of joint point distortion. Meanwhile, a temporal correlation module is proposed to focus on the temporal correlation between past and present frames, taking into account the influence of temporal characteristics in the video sequence. A hierarchical structure is adopted to fuse adjacent features, thus fully mine the 3D information based on the video. The experimental results show that this model significantly improves the human depth estimation performance, especially at the joints.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow. https://github.com/matterport/Mask_RCNN. Accessed 11 Jun 2023
Chen, W., Fu, Z., Yang, D., Deng, J.: Single-image depth perception in the wild. Adv. Neural. Inf. Process. Syst. 29(1), 730–738 (2016)
Jafarian, Y., Park, H.S.: Self-supervised 3D representation learning of dressed humans from social media videos. PAMI (2022)
Li, C., et al.: RADepthNet: reflectance-aware monocular depth estimation. Virtual Reality Intell. Hardware 4(5), 418–431 (2022)
Li, Y., Luo, F., Li, W., Zheng, S., Wu, H.H., Xiao, C.: Self-supervised monocular depth estimation based on image texture detail enhancement. Vis. Comput. 37(9–11), 2567–2580 (2021)
Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12179–12188. IEEE Computer Society (2021)
Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. PAMI (2020)
Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: ICCV, pp. 2304–2314. IEEE (2019)
Saito, S., Simon, T., Saragih, J., Joo, H.: Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3D human digitization. In: CVPR, pp. 84–93. IEEE (2020)
Sanakoyeu, A., Khalidov, V., McCarthy, M.S., Vedaldi, A., Neverova, N.: Transferring dense pose to proximal animal classes. In: CVPR, pp. 5233–5242. IEEE (2020)
Tang, S., Tan, F., Cheng, K., Li, Z., Zhu, S., Tan, P.: A neural network for detailed human depth estimation from a single image. In: ICCV, pp. 7750–7759. IEEE (2019)
Varol, G., et al.: Learning from synthetic humans. In: CVPR, pp. 109–117. IEEE (2017)
Wang, L., Zhao, X., Yu, T., Wang, S., Liu, Y.: NormalGAN: learning detailed 3D human from a single RGB-D image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 430–446. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_26
Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: Icon: Implicit clothed humans obtained from normals. In: CVPR, pp. 13286–13296. IEEE (2022)
Yu, T., Zheng, Z., Guo, K., Liu, P., Dai, Q., Liu, Y.: Function4D: real-time human volumetric capture from very sparse consumer RGBD sensors. In: CVPR, pp. 5746–5756. IEEE (2021)
Zhang, H., Shen, C., Li, Y., Cao, Y., Liu, Y., Yan, Y.: Exploiting temporal consistency for real-time video depth estimation. In: ICCV, pp. 1725–1734. IEEE (2019)
Zhao, T., Pan, S., Gao, W., Sheng, C., Sun, Y., Wei, J.: Attention UNet++ for lightweight depth estimation from sparse depth samples and a single RGB image. Vis. Comput. 38(5), 1619–1630 (2022)
Zheng, Z., Yu, T., Liu, Y., Dai, Q.: PaMIR: parametric model-conditioned implicit representation for image-based human reconstruction. PAMI 44(6), 3170–3184 (2021)
Zoran, D., Isola, P., Krishnan, D., Freeman, W.T.: Learning ordinal relationships for mid-level vision. In: ICCV, pp. 388–396. IEEE (2015)
Acknowledgements
The authors wish to acknowledge the financial support in part by Guangdong Basic and Applied Basic Research Foundation under Grant 2020B1515120047, in part by Guangdong Natural Science Foundation under Grant 2021A1515011632 and 2021A1515012014.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Supplementary material 1 (mp4 2400 KB)
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Q., Zhang, X. (2024). Video-Based Self-supervised Human Depth Estimation. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14495. Springer, Cham. https://doi.org/10.1007/978-3-031-50069-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-50069-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50068-8
Online ISBN: 978-3-031-50069-5
eBook Packages: Computer ScienceComputer Science (R0)