Abstract
In a real world scene objects of interest might be occluded by other objects. Diminished reality (DR) aims to remove such occluders. A popular approach is to acquire the geometry of the occluded scene, and then to render it from the user’s viewpoint, effectively erasing the occluder. However, the approach is ill-suited for scenes with intricate and dynamic geometry, which cannot be acquired quickly, completely, and with only minimal equipment. This paper proposes a method to erase an occluder in a primary video by splicing in pixels from a secondary video. For each frame, the method finds the region in the secondary frame that corresponds to the occluder shadow, and integrates it seamlessly into the primary frame. Precise matching of the occluder contour is achieved by a novel pipeline with a tracking, global alignment, and local alignment stages. The result is a continuous multiperspective frame, which shows most of the scene from the primary viewpoint, except for the part hidden by the occluder, which is shown from the secondary viewpoint. A high quality multiperspective transparency effect is achieved for complex scenes, without the high cost of 3D acquisition. When compared with other DR methods, the proposed method shows fewer artifacts and better continuity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adobe photoshop. https://www.adobe.com/products/photoshop.html. Accessed 30 Apr 2020
Álvarez, H., Arrieta, J., Oyarzun, D.: Towards a diminished reality system that preserves structures and works in real-time. In: VISIGRAPP (4: VISAPP), pp. 334–343 (2017)
Andre, E., Hlavacs, H.: Diminished reality based on 3D-scanning. In: van der Spek, E., Göbel, S., Do, E.Y.-L., Clua, E., Baalsrud Hauge, J. (eds.) ICEC-JCSG 2019. LNCS, vol. 11863, pp. 3–14. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-34644-7_1
Avery, B., Piekarski, W., Thomas, B.H.: Visualizing occluded physical objects in unfamiliar outdoor augmented reality environments. In: Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality, pp. 1–2. IEEE Computer Society (2007)
Barnes, C., Shechtman, E., Goldman, D.B., Finkelstein, A.: The generalized PatchMatch correspondence algorithm. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6313, pp. 29–43. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15558-1_3
Barnum, P., Sheikh, Y., Datta, A., Kanade, T.: Dynamic seethroughs: synthesizing hidden views of moving objects. In: 2009 8th IEEE International Symposium on Mixed and Augmented Reality, pp. 111–114. IEEE (2009)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). https://doi.org/10.1007/11744023_32
Bugeau, A., Bertalmío, M., Caselles, V., Sapiro, G.: A comprehensive framework for image inpainting. IEEE Trans. Image Process. 19(10), 2634–2645 (2010)
Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings, vol. 2, pp. II–II. IEEE (2003)
Enomoto, A., Saito, H.: Diminished reality using multiple handheld cameras. In: Proceedings of ACCV, vol. 7, pp. 130–135 (2007)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Hasegawa, K., Saito, H.: Diminished reality for hiding a pedestrian using hand-held camera. In: 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, pp. 47–52. IEEE (2015)
Herling, J., Broll, W.: High-quality real-time video inpaintingwith pixmix. IEEE Trans. Visual Comput. Graphics 20(6), 866–879 (2014)
Holland, P.W., Welsch, R.E.: Robust regression using iteratively reweighted least-squares. Commun. Stat. Theor. Methods 6(9), 813–827 (1977)
Iizuka, S., Simo-Serra, E., Ishikawa, H.: Globally and locally consistent image completion. ACM Trans. Graph. (ToG) 36(4), 1–14 (2017)
Jampour, M., Li, C., Yu, L.F., Zhou, K., Lin, S., Bischof, H.: Face inpainting based on high-level facial attributes. Comput. Vis. Image Underst. 161, 29–41 (2017)
Kameda, Y., Takemasa, T., Ohta, Y.: Outdoor see-through vision utilizing surveillance cameras. In: Proceedings of the 3rd IEEE/ACM International Symposium on Mixed and Augmented Reality, pp. 151–160. IEEE Computer Society (2004)
Li, Z., Zhu, H., Cao, L., Jiao, L., Zhong, Y., Ma, A.: Face inpainting via nested generative adversarial networks. IEEE Access 7, 155462–155471 (2019)
Li, Z., Wang, Y., Guo, J., Cheong, L.F., Zhou, S.Z.: Diminished reality using appearance and 3d geometry of internet photo collections. In: 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 11–19. IEEE (2013)
Liu, G., Reda, F.A., Shih, K.J., Wang, T.C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: The European Conference on Computer Vision (ECCV) (2018)
Meerits, S., Saito, H.: Real-time diminished reality for dynamic scenes. In: 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, pp. 53–59. IEEE (2015)
Mei, C., Sommerlade, E., Sibley, G., Newman, P., Reid, I.: Hidden view synthesis using real-time visual slam for simplifying video surveillance analysis. In: 2011 IEEE International Conference on Robotics and Automation, pp. 4240–4245. IEEE (2011)
Mori, S., Ikeda, S., Saito, H.: A survey of diminished reality: techniques for visually concealing, eliminating, and seeing through real objects. IPSJ Trans. Comput. Vis. Appl. 9(1), 1–14 (2017). https://doi.org/10.1186/s41074-017-0028-1
Mori, S., Maezawa, M., Ienaga, N., Saito, H.: Diminished hand: a diminished reality-based work area visualization. In: 2017 IEEE Virtual Reality (VR), pp. 443–444. IEEE (2017)
Mori, S., Shibata, F., Kimura, A., Tamura, H.: Efficient use of textured 3d model for pre-observation-based diminished reality. In: 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, pp. 32–39. IEEE (2015)
Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. VISAPP (1) 2(331–340), 2 (2009)
Nakajima, Y., Mori, S., Saito, H.: Semantic object selection and detection for diminished reality based on slam with viewpoint class. In: 2017 IEEE International Symposium on Mixed and Augmented Reality (ISMAR-Adjunct), pp. 338–343. IEEE (2017)
Nocedal, J., Wright, S.: Numerical Optimization. Springer, New York (2006). https://doi.org/10.1007/978-0-387-40065-5
Queguiner, G., Fradet, M., Rouhani, M.: Towards mobile diminished reality. In: 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), pp. 226–231. IEEE (2018)
Rameau, F., Ha, H., Joo, K., Choi, J., Park, K., Kweon, I.S.: A real-time augmented reality system to see-through cars. IEEE Trans. Visual Comput. Graphics 22(11), 2395–2404 (2016)
Singhal, A., et al.: Modern information retrieval: a brief overview. IEEE Data Eng. Bull. 24(4), 35–43 (2001)
Takemura, M., Ohta, Y.: Diminishing head-mounted display for shared mixed reality. In: Proceedings of the 1st International Symposium on Mixed and Augmented Reality, p. 149. IEEE Computer Society (2002)
Tiefenbacher, P., Sirch, M., Rigoll, G.: Mono camera multi-view diminished reality. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–8. IEEE (2016)
Wang, L., Jin, H., Yang, R., Gong, M.: Stereoscopic inpainting: joint color and depth completion from stereo images. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wexler, Y., Shechtman, E., Irani, M.: Space-time video completion. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2004, CVPR 2004, vol. 1, pp. I-I. IEEE (2004)
Wu, M.L., Popescu, V.: Rgbd temporal resampling for real-time occlusion removal. In: Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, p. 7. ACM (2019)
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505–5514 (2018)
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Free-form image inpainting with gated convolution. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4471–4480 (2019)
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330–1334 (2000)
Zokai, S., Esteve, J., Genc, Y., Navab, N.: Multiview paraperspective projection model for diminished reality. In: Proceedings of the 2nd IEEE/ACM International Symposium on Mixed and Augmented Reality, p. 217. IEEE Computer Society (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, C., Popescu, V. (2022). Fast Intra-Frame Video Splicing for Occlusion Removal in Diminished Reality. In: Zachmann, G., Alcañiz Raya, M., Bourdot, P., Marchal, M., Stefanucci, J., Yang, X. (eds) Virtual Reality and Mixed Reality. EuroXR 2022. Lecture Notes in Computer Science, vol 13484. Springer, Cham. https://doi.org/10.1007/978-3-031-16234-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-16234-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16233-6
Online ISBN: 978-3-031-16234-3
eBook Packages: Computer ScienceComputer Science (R0)