Per-Pixel Manifold-Based Color Calibration Technique
Source abstract
Abstract
In this paper, we present a method for obtaining a manifold color correction transform for multiview images. The method can be applied in various scenarios, for correcting the colors of stitched images, adjusting the colors of images obtained in different lighting conditions, and performing virtual view synthesis based on images taken by different cameras or in different conditions. The provided derivation allows us to use the method to correct regular RGB images. The provided solution is specified as a transform matrix that provides the pixel-specific color transformation for each pixel and therefore is more general than the methods described in the literature, which only provide the transformed images without explicitly providing the transform. By providing the transform for each pixel separately, we can introduce a smoothness constraint based on the transformation similarity for neighboring pixels, a feature that is not present in the available literature.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Vision and Imaging · Image Processing Techniques and Applications · Image Enhancement Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Robotics and Machine Intelligence, Poznan University of Technology, pl. M. Skłodowskiej-Curie 5, 60-965 Poznan, Poland
Mucha sp. z o.o., ul. Szelągowska 17, 61-626 Poznan, Poland
Institute of Multimedia Telecommunications, Poznan University of Technology, pl. M. Skłodowskiej-Curie 5, 60-965 Poznan, Poland
Funding
The National Centre for Research and Development in the LIDER Programme · Ministry of Science and Higher Education, Poland
References (34)
Show source-provided references
1. NeRF: Representing scenes as neural radiance fields for view synthesis10.1145/3503250 ↗
2. Wang, P., Liu, Y., Chen, Z., Liu, L., Liu, Z., Komura, T., Theobalt, C., and Wang, W. (2023, January 17–24). F2-nerf: Fast neural radiance field training with free camera trajectories. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00404 ↗
3. Nawaz, A., Kanwal, I., Idrees, S., Imtiaz, R., Jalil, A., Ali, A., and Ahmed, J. (2017, January 11–14). Fusion of color and infrared images using gradient transfer and total variation minimization. Proceedings of the 2nd International Conference on Computer and Communication Systems (ICCCS), Krakow, Poland.10.1109/CCOMS.2017.8075272 ↗
4. Digital photography with flash and no-flash image pairs10.1145/1015706.1015777 ↗
5. Multi-View Stereo: A Tutorial10.1561/0600000052 ↗
6. Global Color Consistency Correction for Large-Scale Images in 3-D Reconstruction10.1109/JSTARS.2022.3167264 ↗
7. Fusion-Based Multiview Color Correction via Minimum Weight-First-Then-Larger Outdegree Target Image Selection10.1109/TGRS.2024.3457887 ↗
8. Spatio-Temporally Consistent Color and Structure Optimization for Multiview Video Color Correction10.1109/TMM.2015.2412879 ↗
9. Chen, Y., Cai, C., and Liu, J. (2006, January 20–24). YUV Correction for Multi-View Video Compression. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.
10. Fezza, S.A., Larabi, M.-C., and Faraoun, K.M. (2013, January 10–12). Coding and rendering enhancement of multi-view video by color correction. Proceedings of the European Workshop on Visual Information Processing (EUVIP), Paris, France.
11. Color calibration of multi-view video plus depth for advanced 3D video10.1007/s11760-015-0761-9 ↗
12. Ganelin, I., and Nasiopoulos, P. (2018, January 7–10). Virtual View Color Estimation for Free Viewpoint TV Applications Using Gaussian Mixture Model. Proceedings of the 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece.10.1109/ICIP.2018.8451211 ↗
13. Multi-Camera Color Correction via Hybrid Histogram Matching10.1109/TCSVT.2020.3038484 ↗
14. Joshi, N. (2004). Color Calibration for Arrays of Inexpensive Image Sensors, Technoly Report, Stanford University. CSTR 2004-02 3/31/04 4/4/04.
15. Camera Color Correction Using Splines10.2352/EI.2024.36.16.COLOR-165 ↗
16. Color Correction and Depth-Based Hierarchical Hole Filling in Free Viewpoint Generation10.1109/TBC.2019.2901391 ↗
17. Color Correction for Immersive Video Applications10.1109/ACCESS.2021.3081870 ↗
18. Ilie, A., and Welch, G. (2005, January 17–21). Ensuring color consistency across multiple cameras. Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, Beijing, China.10.1109/ICCV.2005.88 ↗
19. Color transfer between images10.1109/38.946629 ↗
20. Flynn, J., Neulander, I., Philbin, J., and Snavely, N. (2016). DeepStereo: Learning to Predict New Views From the World’s Imagery. arXiv.10.1109/CVPR.2016.595 ↗
21. Contrast-Aware Color Consistency Correction for Multiple Images10.1109/JSTARS.2022.3183188 ↗
22. Color correction for large-baseline multiview video10.1016/j.image.2017.01.004 ↗
23. Ceulemans, B., Lu, S.-P., Schelkens, P., and Munteanu, A. (2015, January 8–10). Globally optimized multiview video color correction using dense spatio-temporal matching. Proceedings of the 2015 3DTV-Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON), Lisbon, Portugal.10.1109/3DTV.2015.7169356 ↗
24. Liao, D., Qian, Y., and Li, Z.-N. (2016, January 4–8). Semisupervised manifold learning for color transfer between multiview images. Proceedings of the 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico.10.1109/ICPR.2016.7899643 ↗
25. A Transpose-Free Quasi-Minimal Residual Algorithm for Non-Hermitian Linear Systems10.1137/0914029 ↗
26. Saad, Y. (2003). Iterative Methods for Sparse Linear Systems: Second Edition, Society for Industrial and Applied Mathematics.10.1137/1.9780898718003 ↗
27. Kelley, C.T. (1995). Iterative Methods for Linear and Nonlinear Equations, Society for Industrial and Applied Mathematics.10.1137/1.9781611970944 ↗
28. Senoh, T., Kenji, J., Nobuji, T., Hiroshi, Y., and Wegner, K. (2017, January 1–7). View Synthesis Reference Software (VSRS) 4.2 with improved inpainting and hole filing. Proceedings of the ISO/IEC JTC1/SC29/WG11 MPEG2017, Hobart, Australia.
29. Domański, M., Grajek, T., Klimaszewski, K., Kurc, M., Stankiewicz, O., Stankowski, J., and Wegner, K. (2009, January 26–30). Poznań Multiview Video Test Sequences and Camera Parameters M17050. Proceedings of the ISO/IEC JTC1/SC29/WG11, MPEG2009, Xian, China.
30. Domański, M., Dziembowski, A., Kuehn, A., Kurc, M., Łuczak, A., Mieloch, D., Siast, J., Stankiewicz, O., and Wegner, K. (2014, January 13–17). Poznan Blocks—A Multiview Video Test Sequence and Camera Parameters for Free Viewpoint Television M32243. Proceedings of the ISO/IEC JTC1/SC29/WG11 MPEG2014, San Jose, CA, USA.10.1109/3DTV.2014.6874727 ↗
31. High-quality video view interpolation using a layered representation10.1145/1015706.1015766 ↗
32. Goorts, P. (2014). The Genk Dataset, Real-Time Adaptive Plane Sweeping for Free Viewpoint Navigation in Soccer Scenes. [Ph.D. Thesis, Hasselt University].
33. Senoh, T., Tetsutani, N., and Yasuda, H. (2019, January 25–29). [MPEG-I Visual] Proposal of Trimming and Color Matching of Multi-View Sequences M47170. Proceedings of the ISO/IEC JTC1/SC29/WG11 MPEG2019, Geneva, Switzerland.
34. Afifi, M., and Digital Photography with Flash and No-Flash Image Pairs (2025, March 07). MATLAB Central File Exchange. Available online: https://www.mathworks.com/matlabcentral/fileexchange/62625-digital-photography-with-flash-and-no-flash-image-pairs.