Support-Gated Dense Hypothesis Selection for Three-View Aerial Video Stitching

Xuebing Wang

doi:10.62677/IJETAA.2609153

Authors

Xuebing Wang School of New Energy, Inner Mongolia University of Technology, Ordos 017010, China Author

DOI:

https://doi.org/10.62677/IJETAA.2609153

Keywords:

Video stitching, Three-view geometry, Dense warps, Temporal transport, Independent evaluation

Abstract

Three-view aerial video stitching requires spatial alignment and control of historical warp drift. We evaluate a target-training-free dense hypothesis-selection system using released LoFTR and PixelStitch components, observed third-view support, and a bounded historical proposal. Published synthetic depth and real laser geometry evaluate the actual backward sampler independently of the matcher. A locally frozen study uses six held-out SynDrone towns, three held-out ETH3D rig scenes and five estimator seeds. The guarded model improves synthetic success within 3 pixels from 70.576% to 71.033%, a 0.456-percentage-point difference with a descriptive town-bootstrap 95% interval of [0.187, 0.747] and an exact paired sign-randomization p = 0.03125. Real-rig success changes from 92.435% to 92.604%, but an adapted official PixelStitch control achieves 93.973%. Ablations attribute nearly all same-backbone gain to current spatial verification; the extra historical mechanism contributes little and does not consistently beat the spatial-only model. Complete fresh-matching inference and common rendering take 6.785 seconds per triplet, versus 4.530 for the pairwise control on the measured configuration. Two public multi-UAV clips demonstrate wide-angle output without independent dense accuracy truth. The evidence supports a modest spatial-selection improvement, not a general advantage from temporal memory, real-time operation or universal superiority.

Downloads

Download data is not yet available.

References

M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography”, Communications of the ACM, vol. 24, no. 6, pp. 381–395, 1981. DOI: 10.1145/358669.358692.

M. Brown and D. G. Lowe, “Automatic Panoramic Image Stitching using Invariant Features”, International Journal of Computer Vision, vol. 74, no. 1, pp. 59–73, 2007. DOI: 10.1007/s11263-006-0002-3.

C.-H. Chang, Y. Sato, and Y.-Y. Chuang, “Shape-Preserving Half-Projective Warps for Image Stitching”, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3254–3261, 2014. DOI: 10.1109/cvpr.2014.422.

F. Zhang and F. Liu, “Parallax-Tolerant Image Stitching”, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3262–3269, 2014. DOI: 10.1109/cvpr.2014.423.

L. Nie, C. Lin, K. Liao, S. Liu, and Y. Zhao, “Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images”, IEEE Transactions on Image Processing, vol. 30, pp. 6184–6197, 2021. DOI: 10.1109/tip.2021.3092828.

L. Nie, C. Lin, K. Liao, S. Liu, and Y. Zhao, “Parallax-Tolerant Unsupervised Deep Image Stitching”, in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7365–7374, 2023. DOI: 10.1109/iccv51070.2023.00680.

H. Jin, L. Nie, C. Lin, X. Feng, and Y. Zhao, “PixelStitch: Structure-Preserving Pixel-Wise Bidirectional Warps for Unsupervised Image Stitching”, in 2025 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 28125–28134, 2025. DOI: 10.1109/iccv51701.2025.02611.

P. J. Burt and E. H. Adelson, “A multiresolution spline with application to image mosaics”, ACM Transactions on Graphics, vol. 2, no. 4, pp. 217–236, 1983. DOI: 10.1145/245.247.

Z. Zhang, X. Yu, and X. Yang, “Image alignment using mixture models for discontinuous deformations”, Signal Processing, vol. 195, Art. no. 108467, 2022. DOI: 10.1016/j.sigpro.2022.108467.

T. Liao, C. Wang, L. Li, G. Liu, and N. Li, “Parallax-tolerant image stitching via segmentation-guided multi-homography warping”, Signal Processing, vol. 230, Art. no. 109860, 2025. DOI: 10.1016/j.sigpro.2024.109860.

L. Qiu, C. Liu, G. Li, X. Dong, F. Xie, and Z. Shi, “Unsupervised Deep Image Stitching for Remote Sensing: Aligning Features Across Large-Scale Geometric Distortions”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 25305–25324, 2025. DOI: 10.1109/jstars.2025.3609808.

L. Qiu, F. Xie, C. Liu, X. Che, and Z. Shi, “Radiation-Tolerant Unsupervised Deep Image Stitching for Remote Sensing”, IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1–21, 2025. DOI: 10.1109/tgrs.2025.3605270.

L. Nie, Y. Mei, K. Liao, Y. Xu, C. Lin, and B. Xiao, “Robust Image Stitching With Optimal Plane”, IEEE Transactions on Visualization and Computer Graphics, vol. 32, no. 7, pp. 5156–5166, 2026. DOI: 10.1109/tvcg.2026.3663425.

J. Sun, Z. Shen, Y. Wang, H. Bao, and X. Zhou, “LoFTR: Detector-Free Local Feature Matching with Transformers”, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8918–8927, 2021. DOI: 10.1109/cvpr46437.2021.00881.

P. Lindenberger, P.-E. Sarlin, and M. Pollefeys, “LightGlue: Local Feature Matching at Light Speed”, in 2023 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 17581–17592, 2023. DOI: 10.1109/iccv51070.2023.01616.

J. Edstedt, Q. Sun, G. Bökman, M. Wadenbäck, and M. Felsberg, “RoMa: Robust Dense Feature Matching”, in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19790–19800, 2024. DOI: 10.1109/cvpr52733.2024.01871.

Y. Wang, X. He, S. Peng, D. Tan, and X. Zhou, “Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed”, in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21666–21675, 2024. DOI: 10.1109/cvpr52733.2024.02047.

D. Barath, J. Noskova, M. Ivashechkin, and J. Matas, “MAGSAC++, a Fast, Reliable and Accurate Robust Estimator”, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1301–1309, 2020. DOI: 10.1109/cvpr42600.2020.00138.

K. Sun, J. Yu, W. Tao, X. Li, C. Tang, and Y. Qian, “A unified feature-spatial cycle consistency fusion framework for robust image matching”, Information Fusion, vol. 97, Art. no. 101810, 2023. DOI: 10.1016/j.inffus.2023.101810.

W. Jiang and J. Gu, “Video stitching with spatial-temporal content-preserving warping”, in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 42–48, 2015. DOI: 10.1109/cvprw.2015.7301374.

L. Nie, C. Lin, K. Liao, Y. Zhang, S. Liu, R. Ai, and Y. Zhao, “Eliminating Warping Shakes for Unsupervised Online Video Stitching”, in Computer Vision – ECCV 2024, pp. 390–407, 2025. DOI: 10.1007/978-3-031-73235-5_22.

L. Nie, C. Lin, K. Liao, Y. Zhang, S. Liu, and Y. Zhao, “StabStitch++: Unsupervised Online Video Stitching With Spatiotemporal Bidirectional Warps”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 9, pp. 7443–7456, 2025. DOI: 10.1109/tpami.2025.3568829.

X. Yun, F. Yu, K. Dong, and Y. Sun, “Unsupervised video stitching via spatiotemporal coupling with temporal propagation and dynamic memory”, Knowledge-Based Systems, vol. 344, Art. no. 116048, 2026. DOI: 10.1016/j.knosys.2026.116048.

T. Kroeger, R. Timofte, D. Dai, and L. Van Gool, “Fast Optical Flow Using Dense Inverse Search”, Lecture Notes in Computer Science, pp. 471–488, 2016. DOI: 10.1007/978-3-319-46493-0_29.

Z. Teed and J. Deng, “RAFT: Recurrent All-Pairs Field Transforms for Optical Flow”, Lecture Notes in Computer Science, pp. 402–419, 2020. DOI: 10.1007/978-3-030-58536-5_24.

JYe9, “Multi-Camera Multi-Vehicle Tracking System (UAV Dataset)”, n.d. [Online]. Available: https://huggingface.co/datasets/jye9/Multi-Camera-Multi-Vehicle-Tracking-System. Accessed: Sep. 21, 2026.

A. Agarwala, M. Dontcheva, M. Agrawala, S. Drucker, A. Colburn, B. Curless, D. Salesin, and M. Cohen, “Interactive digital photomontage”, ACM Transactions on Graphics, vol. 23, no. 3, pp. 294–302, 2004. DOI: 10.1145/1015706.1015718.

G. Rizzoli, F. Barbato, M. Caligiuri, and P. Zanuttigh, “SynDrone – Multi-modal UAV Dataset for Urban Scenarios”, in 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2202–2212, 2023. DOI: 10.1109/iccvw60793.2023.00235.

T. Schops, J. L. Schonberger, S. Galliani, T. Sattler, K. Schindler, M. Pollefeys, and A. Geiger, “A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos”, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2538–2547, 2017. DOI: 10.1109/cvpr.2017.272.

S. Afridi, S. Bullock, A. Jarabo Penas, and L. Laporte Devylder, “MP-ZEBRA: Multi-Perspective Dataset of Plains Zebras”, n.d. [Online]. Available: https://huggingface.co/datasets/edouard-rolland/multi-perspective-dataset-plain-zebras. Accessed: Sep. 21, 2026.