Research output per year
Research output per year
Personal profile
Artistic and research interests
Prof. Juho Kannala (PhD 2010) is an Assistant Professor at Aalto University. He defended his PhD thesis in 2010 in the University of Oulu. From 2011 until 2014 he was a postdoctoral researcher funded by the Academy of Finland. In 2012 he was a visiting researcher in INRIA Grenoble working with Dr. Peter Sturm and in 2014 he visited the Mathematical Imaging Group at Lund University. His scientific research is focused on computer vision and covers geometric aspects in 3D vision as well as topics in recognition and semantic image analysis. His work on geometric camera calibration is widely cited and the related software is used by researchers and practitioners worldwide. He has authored or co-authored more than 100 peer-reviewed scientific articles and his H-index is 35 according to Google Scholar.
Keywords
- computer vision
- machine learning
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
-
SDG 3 Good Health and Well-being -
SDG 4 Quality Education
Fingerprint
Dive into the research topics where Juho Kannala is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
Research output
-
Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models
Dong, H., Liu, M., Zhou, K., Chatzi, E., Kannala, J., Stachniss, C. & Fink, O., 2026, In: IEEE Transactions on Pattern Analysis and Machine Intelligence. 48, 5, p. 5672-5691 20 p.Research output: Contribution to journal › Article › Scientific › peer-review
Open Access12 Citations (Scopus) -
Grouped Discrete Representation for Object-Centric Learning
Zhao, R., Wang, H., Kannala, J. & Pajarinen, J., 2026, Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, ECML PKDD 2025, Proceedings. Ribeiro, R. P., Soares, C., Gama, J., Pfahringer, B., Japkowicz, N., Larrañaga, P., Jorge, A. M. & Abreu, P. H. (eds.). Springer, p. 465-480 16 p. (Lecture notes in computer science; vol. 16018).Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review
Open AccessFile2 Downloads (Pure) -
Pose-Guided Geometric Refinement for Feed-Forward 3D Gaussian Splatting
Wang, Z., Ji, X., Zhang, Y., Rahtu, E. & Kannala, J., 2027, Pattern Recognition - 28th International Conference, ICPR 2026, Proceedings. De Marsico, M., Ho, T. K., Jurie, F., Liu, C.-L., Lopresti, D., Nyström, I., Ogier, J.-M., Ross, A. & Wang, L. (eds.). Springer, p. 217-231 15 p. (Lecture Notes in Computer Science; vol. 16823 LNCS).Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review
-
Predicting Video Slot Attention Queries from Random Slot-Feature Pairs
Zhao, R., Li, J., Kannala, J. & Pajarinen, J., 2026, Proceedings of the AAAI Conference on Artificial Intelligence. Koenig, S., Jenkins, C. & Taylor, M. E. (eds.). 16 ed. Association for the Advancement of Artificial Intelligence, p. 13208-13216 9 p. (Proceedings of the AAAI Conference on Artificial Intelligence; vol. 40, no. 16).Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review
Open Access -
SceneShine: Illumination-aware Human Scene Gaussian Re-Splatting from Mobile Device Video
Ren, X., Wang, W., Nguyen, M. N., Kannala, J. & Rahtu, E., 2026, Proceedings - 2026 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2026. IEEE, p. 8302-8312 11 p. (Proceedings - IEEE Workshop on Applications of Computer Vision).Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review
-
R2B ORCA/Kannala/T31331: ORCA Orthopedic Camera Assisted Surgery
Kannala, J. (Principal investigator), Tikkakoski, T. (Project Member) & Pitkänen, V. (Project Member)
01/06/2025 → 31/05/2027
Project: BF R2B
-
BERMUDA /Kannala: BERMUDA : Spatial Artificial Intelligence for Visual Geometry and Immersion
Kannala, J. (Principal investigator), Fang, J. (Project Member), Melekhov, I. (Project Member), Wang, S. (Project Member), Yakovleva, A. (Project Member), Wang, Z. (Project Member) & Zhao, Y. (Project Member)
01/09/2024 → 31/08/2028
Project: RCF Academy Project
-
-: Finnish Center for Artificial Intelligence
Kannala, J. (Principal investigator)
01/01/2023 → 31/12/2026
Project: Academy of Finland: Other research funding
-
MATINE 3D-mallinnus/Kannala: Sisätilojen ja avoimen ympäristön 3D-mallinnus maanpuolustuksessa
Kannala, J. (Principal investigator), Wang, S. (Project Member), Taka, V. (Project Member), Kilpeläinen, J.-M. (Project Member) & Hukkanen, J. (Project Member)
01/04/2024 → 31/12/2025
Project: Other Domestic (20 FC)
-
Energy efficient machine perception /Kannala 31.12.2025: Energy efficient perception
Kannala, J. (Principal investigator), Zhang, Y. (Project Member), Yakovleva, A. (Project Member), Tran, L. (Project Member), Turkulainen, M. (Project Member), Taka, V. (Project Member), Wang, Z. (Project Member), Makwana, D. (Project Member), Häkkinen, I. (Project Member), Melekhov, I. (Project Member), Fang, J. (Project Member), Pärssinen, H. (Project Member), Ferranti, L. (Project Member) & Kilpeläinen, J.-M. (Project Member)
01/01/2023 → 31/12/2025
Project: RCF Academy Project targeted call
Datasets
-
ADVIO: An Authentic Dataset for Visual-Inertial Odometry
Cortes Reina, S. (Creator), Solin, A. (Creator), Rahtu, E. (Creator) & Kannala, J. (Creator), Zenodo, 25 Jul 2018
DOI: 10.5281/zenodo.1320824, https://github.com/AaltoVision/ADVIO and one more link, https://zenodo.org/record/1476931 (show fewer)
Dataset
-
Deep Automodulators
Heljakka, A. (Creator), Hou, Y. (Creator), Kannala, J. (Creator) & Solin, A. (Creator), Zenodo, 11 Jun 2020
DOI: 10.5281/zenodo.4298893, https://doi.org/10.5281/zenodo.4298894 and 2 more links, https://arxiv.org/abs/1912.10321, https://github.com/AaltoVision/automodulator (show fewer)
Dataset
-
Unstructured multi-view depth estimation using mask-based multiplane representation
Hou, Y. (Creator), Solin, A. (Creator) & Kannala, J. (Creator), Zenodo, 4 Apr 2019
DOI: 10.5281/zenodo.2628419, https://zenodo.org/api/records/2628420
Dataset
-
Pioneer Networks: Progressively Growing Generative Autoencoder
Ari, H. (Creator), Solin, A. (Creator) & Kannala, J. (Creator), Zenodo, 10 Oct 2018
DOI: 10.5281/zenodo.1455187, https://zenodo.org/api/records/1455188
Dataset
-
RP1M: A Large-Scale Motion Dataset for Piano Playing with Bimanual Dexterous Robot Hands
Chen, L. (Creator), Zhao, Y. (Creator), Schneider, J. (Creator), Gao, Q. (Creator), Kannala, J. (Creator), Schölkopf, B. (Creator), Pajarinen, J. (Creator) & Büchler, D. (Creator), Edmond, 30 Oct 2024
DOI: 10.17617/3.xce8nx, https://edmond.mpg.de/citation?persistentId=doi:10.17617/3.XCE8NX
Dataset
Prizes
-
Primus Young Doctor in the Conferment Seremony of the University of Oulu
Kannala, J. (Recipient), 2013
Prize: Award or honor granted for academic or artistic career
-
Tobii best paper award
Ylimäki, M. (Recipient), Kannala, J. (Recipient) & Heikkilä, J. (Recipient), 2017
Prize: Award or honor granted for a specific work
Activities
-
IET Computer Vision (Journal)
Kannala, J. (Editor)
2017 → …Activity: Publication peer-review and editorial work types › Membership of an editorial board
-
Pre-examiner and a member of the Ph.D. thesis committee, University of Lorraine / INRIA Nancy
Kannala, J. (Examiner)
2015Activity: Academic assessments › Pre-examination of doctoral thesis or acting as opponent to doctoral students or membership of doctoral thesis committee or board
Press/Media
-
Investigators from Aalto University Target Imaging Technology (Hscnet Plus Plus : Hierarchical Scene Coordinate Classification and Regression for Visual Localization With Transformer)
04/03/2024
1 item of Media coverage
Press/Media: Media appearance
-
Learning Latent Image Representations with Prior Knowledge
02/12/2022
1 item of Media coverage
Press/Media: Media appearance
-
Sample-Efficient Methods for Real-World Deep Reinforcement Learning
Solin, A., Ilin, A. & Kannala, J.
25/05/2022
1 item of Media coverage
Press/Media: Media appearance
-
Models and Methods for Inertial and Visual Odometry
20/10/2021
1 item of Media coverage
Press/Media: Media appearance
-
Visual communication in ubiquitous computing: from smartphones to pervasive displays
Oulasvirta, A., Sethi, M., Di Francesco, M. & Kannala, J.
30/04/2021
1 item of Media coverage
Press/Media: Media appearance