Selected Publications

H Chefer, O Lang, M Geva, V Polosukhin, A Shocher, M Irani, I Mosseri, L Wolf, The hidden language of diffusion models. International Conference on Learning Representations (ICLR), May 2024.

[Paper] [Project page]
O Lang, D Yaya-Stupp, I Traynis, H Cole-Lewis, CR Bennett, CR Lyles, C Lau, M Irani, C Semturs, DR Webster, GS Corrado, A Hassidim, Y Matias, Y Liu, N Hammel, B Babenko, Using generative AI to investigate medical imagery models and datasets. eBioMedicine volume 102, April 2024.

[Paper]
G Buzaglo, N Haim, G Yehudai, G Vardi, Y Oz, Y Nikankin, M Irani, Deconstructing data reconstruction: Multiclass, weight decay and general losses. Conference on Neural Information Processing Systems (NeurIPS), December 2023.

[Paper] [Project page]
R Paiss, A Ephrat, O Tov, S Zada, I Mosseri, M Irani, T Dekel, Teaching clip to count to ten. IEEE/CVF International Conference on Computer Vision (ICCV), October 2023.

[Paper]
Y Nikankin, N Haim, M Irani, SinFusion: Training Diffusion Models on a Single Image or Video, International Conference on Machine Learning (ICML), July 2023.

[Paper] [Project page]
B Kawar, S Zada, O Lang, O Tov, H Chang, T Dekel, I Mosseri, M Irani, Imagic: Text-based real image editing with diffusion models, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023.

[Paper] [Project page]
G Buzaglo, N Haim, G Yehudai, G Vardi, M Irani, Reconstructing Training Data from Multiclass Neural Networks. Workshop on the pitfalls of limited data and computation for Trustworthy ML, ICLR 2023.

[Paper]
N Haim, G Vardi, G Yehudai, O Shamir, M Irani, Reconstructing training data from trained neural networks, Conference on Neural Information Processing Systems (NeurIPS), December 2022.

[Paper] [Project page]
E Naor, I Antebi, S Bagon, M Irani, Combining Internal and External Constraints for Unrolling Shutter in Videos, European Conference on Computer Vision (ECCV), October 2022.

[Paper] [Project page]
N Haim, B Feinstein, N Granot, A Shocher, S Bagon, T Dekel, M Irani, Diverse generation from a single video made possible, European Conference on Computer Vision (ECCV), October 2022.

[Paper] [Project page]
S Zada, I Benou, M Irani, Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images, International Conference on Machine Learning (ICML), July 2022.

[Paper]
G Kupershmidt, R Beliy, G Gaziv, M Irani, A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activity, arXiv preprint arXiv:2206.03544, June 2022.

[Paper] [Project page]
N Granot, B Feinstein, A Shocher, S Bagon, M Irani, Drop the GAN: In defense of patches nearest neighbors as single image generative models, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.

[Paper] [Project page]
G Gaziv, R Beliy, N Granot, A Hoogi, F Strappini, T Golan, M Irani, Self-Supervised Natural Image Reconstruction and Large-Scale Semantic Classification from Brain Activity, NeuroImage, 119121, March 2022.

[Paper] [Project page]
R Mokady, M Yarom, O Tov, O Lang, D Cohen-Or, T Dekel, M Irani, Self-Distilled StyleGAN: Towards Generation from Internet Photos, ACM SIGGRAPH - July 2022.

[Paper] [Project page]
O Lang, Y Gandelsman, M Yarom, Y Wald, G Elidan, A Hassidim, W.T. Freeman, P. Isola, A. Globerson, M. Irani, I. Mosseri, Explaining in Style: Training a GAN to explain a classifier in StyleSpace, IEEE/CVF International Conference on Computer Vision (ICCV), October 2021.

[Paper] [Project page]
G Gaziv, M Irani, More than meets the eye: Self-supervised depth reconstruction from brain activity, arXiv preprint arXiv:2106.05113, September 2021.

[Paper]
Liad Pollak Zuckerman, Eyal Naor, George Pisha, Shai Bagon, Michal Irani, Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning, European Conference on Computer Vision (ECCV), August 2020.
[Paper] [Project page]
Assaf Shocher, Yossi Gandelsman, Inbar Mosseri, Michal Yarom, Michal Irani, William T. Freeman, Tali Dekel, Semantic Pyramid for Image Generation, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
[Paper] [Project page]
Sagie Benaim, Ariel Ephrat, Oran Lang, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Michal Irani, Tali Dekel, SpeedNet: Learning the Speediness in Videos, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
[Paper] [Project page]
Assaf Shocher, Ben Feinstein, Niv Haim, Michal Irani, From Discrete to Continuous Convolution Layers, arXiv preprint arXiv:2006.11120.
[Paper]
Roman Beliy*, Guy Gaziv*, Assaf Hoogi, Fracesca Strappini, Tal Golan, Michal Irani, From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI, Conference on Neural Information Processing Systems (NeurIPS), December 2019.
*Equal contribution
[Paper] [Project page]
Sefi Bell-Kligler, Assaf Shocher, Michal Irani, “KernelGAN”: Blind Super-Resolution Kernel Estimation using an Internal-GAN, Conference on Neural Information Processing Systems (NeurIPS), December 2019.
[Paper] [Project page]
Yosef Gandelsman, Assaf Shocher, Michal Irani, "Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.

[Paper] [Project page]
Assaf Shocher, Shai Bagon, Phillip Isola, Michal Irani, InGAN: Capturing and Remapping the "DNA" of a Natural Image, International Conference on Computer Vision (ICCV), October 2019.

[Paper] [Project page]

An earlier version of this paper appeared in 2018 as:

Assaf Shocher, Shai Bagon, Phillip Isola, Michal Irani, Internal Distribution Matching for Natural Image Retargeting, arXiv preprint arXiv:1812.00231v1 [Paper]
Assaf Shocher, Nadav Cohen, Michal Irani. “Zero-Shot” Super-Resolution using Deep Internal Learning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.

[Paper] [Project page]
Michal Irani. “Blind” Visual Inference by composition. Pattern Recognition Letters, Special Prize Issue. December 2017.
* This paper summarizes my Maria Petrou Prize Talk (prize awarded to me by IAPR).

[Paper]
Yuval Bahat, Netalee Efrat, Michal Irani. Non-Uniform Blind Deblurring by Reblurring. International Conference on Computer Vision (ICCV), October 2017.

[Paper] [Project page]
Michal Yarom, Michal Irani. Temporal-Needle: A view and appearance invariant video descriptor, Arxiv 2016.

[Paper] [Project page]
Yuval Bahat, Michal Irani. Blind Dehazing Using Internal Patch Recurrence. International Conference on Computational Photography (ICCP), May 2016.

[Paper] [Project page]
Or Lotan, Michal Irani. Needle-Match: Reliable Patch Matching Under High Uncertainty, International Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.

[Paper]
Tali Dekel, Tomer Michaeli, Michal Irani, William T. Freeman, Revealing & Modifying Non-Local Variations in a Single Image. ACM Transactions on Graphics (TOG). Proc. SIGGRAPH Asia 2015

[Paper] [Project page + Code]
A. Faktor and M. Irani, Video Segmentation by Non-Local Consensus Voting. British Machine Vision Conference (BMVC), September 2014

[Paper] [Project page + Code ]
T. Michaeli and M. Irani, Blind Deblurring Using Internal Patch Recurrence. European Conference on Computer Vision (ECCV), September 2014.

[Paper] [Project page + Code]
A. Faktor and M. Irani, “Clustering by Composition” – Unsupervised Discovery of Image Categories. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 36(6): 1092-1106, June 2014.

[Paper] [Project page + Code]
A. Faktor and M. Irani, Co-Segmentation by Composition. International Conference on Computer Vision (ICCV), October 2013.

[Paper] [Project page + Code ]
T. Michaeli and M. Irani, Nonparametric Blind Super-Resolution. International Conference on Computer Vision (ICCV), October 2013.

[Paper] [Project page]
M. Zontak, I. Mosseri and M. Irani, Separating Signal from Noise using Patch Recurrence Across Scales, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2013.

[Paper] [Project page]
I. Mosseri, M. Zontak and M. Irani, Combining the Power of Internal and External Denoising, IEEE International Conference on Computational Photography (ICCP), April 2013.

[Paper]
A. Faktor and M. Irani, “Clustering by Composition” – Unsupervised Discovery of Image Categories. European Conference on Computer Vision (ECCV), October 2012

[Paper] [Project page + Code ]
M. Zontak and M. Irani, Internal Statistics of a Single Natural Image. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2011.

[Paper] [Project page]
O. Shahar, A. Faktor and M. Irani, Space-Time Super-Resolution from a Single Video. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2011.

[Paper] [Project page]
E. Shechtman, A. Rav-Acha, M. Irani and S. Seitz, Regenerative Morphing. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2010.

[Paper] [Project page]
S. Bagon, O. Brostovsky, M. Galun and M. Irani, Detecting and Sketching the Common. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2010.

[Paper]
N. Ben-Eliezer, M. Irani, and L. Frydman, Super-Resolved Spatially Encoded Single-Scan 2D MRI. Magnetic Resonance in Medicine 63:1594–1600 (2010).

[Paper]
D. Glasner, S. Bagon, and M. Irani, Super-Resolution from a Single Image. International Conference on Computer Vision (ICCV), October 2009.

[Paper] [Project page]
S. Bagon, O. Boiman and M. Irani, What is a Good Image Segment? A Unified Approach to Segment Extraction. European Conference on Computer Vision (ECCV), October 2008.

[Paper] [Project page]
D. Simakv, Y. Caspi, E. Shechtman and M. Irani, Summarizing Visual Data Using Bidirectional Similarity. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2008.

[Paper] [Project page]
O. Boiman, E. Shechtman and M. Irani, In Defense of Nearest-Neighbor Based Image Classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2008 .

[Paper]
L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, Actions as Space-Time Shapes. In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 29(12): 2247-2253, December 2007.

[Paper] [Project page]

_{(A preliminary version of this paper appeared in ICCV 2005.)}
O. Boiman and M. Irani, Detecting Irregularities in Images and in Video. International Journal of Computer Vision (IJCV), 74(1), 17–31, August 2007.

[Paper] [Project page]
E. Shechtman and M. Irani, Space-time behavior based correlation – OR –
How to tell if two underlying motion fields are similar without computing them? IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 29(11): 2045-2056, November 2007.

[Paper] [Project page]
Y. Wexler, E. Shechtman and M. Irani, Space-Time Completion of Video . In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), March 2007.

[Paper] [Project page]
E. Shechtman and M. Irani, Matching Local Self-Similarities across Images and Videos. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2007.

[Paper] [Project page]
O. Boiman and M. Irani, Similarity by Composition. Neural Information Processing Systems (NIPS), Vancouver, December 2006.

[Paper] [+Appendix] [Project page]
Y. Ukrainitz and M. Irani, Aligning Sequences and Actions by Maximizing Space-Time Correlations. European Conference on Computer Vision (ECCV), May 2006.

[Paper] [Project page]
L. Zelnik-Manor and M. Irani, On single-Sequence and Multi-Sequence Factorizations. International Journal of Computer Vision (IJCV), 67(3): 313-326, May 2006.

[Paper]
L. Zelnik-Manor and M. Irani, Statistical Analysis of Dynamic Actions. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 28(9): 1530--1535, September 2006.

[Paper]
L. Zelnik-Manor, M. Machline, and M. Irani, Multi-body Factorization With Uncertainty: Revisiting Motion Consistency. International Journal of Computer Vision (IJCV), 68(1): 27-41 (special issue on Vision and Modeling of Dynamics Scenes), June 2006.

[Paper]
Y. Caspi, D. Simakov, and M. Irani, Feature-Based Sequence-to-Sequence Matching. International Journal of Computer Vision (IJCV), 68(1): 53-64 (special issue on Vision and Modeling of Dynamics Scenes), June 2006.

[Paper] [Project page]
B. Sarel and M. Irani, Separating Transparent Layers of Repetitive Dynamic Behaviors. IEEE International Conference on Computer Vision (ICCV), Beijing, October 2005.

[Paper] [Project page]
E. Shechtman and M. Irani, Space-Time Behavior Based Correlation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2005.

[Paper] [Project page]
M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri, Actions as Space-Time Shapes. IEEE International Conference on Computer Vision (ICCV), Beijing, October 2005.

[Paper] [Project page]
O. Boiman and M. Irani, Detecting Irregularities in Images and in Video. IEEE International Conference on Computer Vision (ICCV), Beijing, October 2005.

[Paper] [Project page]

_{* Received the Honorable Mention for the 2005 Marr Prize.}
E. Shechtman, Y. Caspi, and M. Irani, Space-Time Super-Resolution. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 27(4): 531-545, April 2005.

[Paper] [Project page]
L. Zelnik-Manor and M. Irani, Temporal Factorization Vs. Spatial Factorization. European Conference on Computer Vision (ECCV), May 2004.

[Paper]
Y. Wexler, E. Shechtman, and M. Irani, Space-Time Video Completion. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2004.

[Paper] [Project page]

_{* Received the best-poster prize at CVPR'2004.}
B. Sarel and M. Irani, Separating Transparent Layers through Layer Information Exchange. European Conference on Computer Vision (ECCV), May 2004.

[Paper] [Project page]
L. Zelnik-Manor and M. Irani, Degeneracies, Dependencies and their Implications in Multi-body and Multi-Sequence Factorizations. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2003

[Paper]
Multiview constraints on homographies
L Zelnik-Manor; Michal Irani (2002) IEEE Transactions on Pattern Analysis and Machine Intelligence. 24, 2, p. 214-223 Abstract
The image motion of a planar surface between two camera views is captured by a homography (a 2D projective transformation). The homography depends on the intrinsic and extrinsic camera parameters, as well as on the 3D plane parameters. While camera parameters vary across different views, the plane geometry remains the same. Based on this fact, we derive linear subspace constraints on the relative homographies of multiple (greater than or equal to 2) planes across multiple views. The paper has three main contributions: 1) We show that the collection of all relative homographies (homologies) of a pair of planes across multiple views, spans a 4-dimensional linear subspace. 2) We show how this constraint can be extended to the case of multiple planes across multiple views. 3) We show that, for some restricted cases of camera motion, linear subspace constraints apply also to the set of homographies of a single plane across multiple views. All the results derived in this paper are true for uncalibrated cameras. The possible utility of these multiview constraints for improving homography estimation and for detecting nonrigid motions are also discussed.
L. Zelnik-Manor and M. Irani, Multi-View Constraints on Homographies. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 24, No. 2, pp. 214 223, February 2002.

[Paper]
P. Anandan and M. Irani, Factorization with Uncertainty . International Journal of Computer Vision (IJCV), 49(2-3): 101-116, September 2002.

[Paper]
M. Irani, P. Anandan, and Meir Cohen, Direct Recovery of Planar-Parallax from Multiple Frames . IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 24, No. 11, pp. 1528 1534, November 2002.

[Paper]
Y. Caspi and M. Irani, Aligning Non-Overlapping Sequences. International Journal of Computer Vision (IJCV), Vol. 48, No. 1, pp. 39-51, 2002.

[Paper] [Project page]

* A shorter version appeared in ICCV’2001, and received the Honorable Mention for the 2001 Marr Prize.”
M. Irani, Multi-Frame Correspondence Estimation Using Subspace Constraints . International Journal of Computer Vision (IJCV), Vol. 48, No. 3, pp. 173 194, July/August 2002.

[Paper]
M. Irani, T. Hassner, and P. Anandan, What Does the Scene Look Like from a Scene Point ? European Conference on Computer Vision (ECCV), May 2002.

[Paper]
Y. Caspi and M. Irani, Spatio-Temporal Alignment of Sequences. IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 24, No. 11, pp. 1409-1424, November 2002.

[Paper] [Project page]
E. Shechtman, Y. Caspi, and M. Irani, Increasing Space-Time Resolution in Video . European Conference on Computer Vision (ECCV), May 2002

[Paper] [Project page]

_{* Received the best-paper prize at ECCV'2002.}
Caspi, Y; Irani, M (2001). Alignment of non-overlapping sequences. Eighth Ieee International Conference On Computer Vision, Vol Ii, Proceedings. 76-83.

[Paper] [Project page]

_{* Received the Honorable Mention for the 2001 Marr Prize.}
L. Zelnik-Manor and M. Irani, Event-Based Video Analysis . IEEE Conference on Computer Vision and Pattern Recognition (CVPR), December 2001.

[Paper]
Y. Caspi, M. Irani: Step towards Sequence-to-Sequence Alignment. CVPR 2000: 2682-2689

[Paper]
M. Irani and P. Anandan, Factorization with Uncertainty . European Conference on Computer Vision (ECCV), June 2000.

[Paper]

_{* Received the best-paper prize at ECCV'2000.}
L. Zelnik-Manor and M. Irani, Multi-Frame Estimation of Planar Motion . IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 22, No. 10, pp. 1105-1116, October 2000.

[Paper]
M. Irani, P. Anandan, M. Cohen: Direct Recovery of Planar-Parallax from Multiple Frames. Workshop on Vision Algorithms 1999: 85-99

[Paper]
L. Zelnik-Manor, M. Irani: Multi-View Subspace Constraints on Homographies. ICCV 1999: 710-715

[Paper]
M. Irani: Multi-Frame Optical Flow Estimation using Subspace Constraints. ICCV 1999: 626-633

[Paper]
L. Zelnik-Manor, M. Irani: Multi-Frame Alignment of Planes. CVPR 1999: 1151-1156

[Paper]
M. Irani and P. Anandan, About Direct Methods. ICCV workshop on Vision Algorithms, pp. 267-277, Corfu, September 1999.

[Paper]
D. Weinshall, P. Anandan, and M. Irani, From Ordinal to Euclidean Reconstruction with Partial Scene Calibration. ECCV'98 Workshop on 3D Structure from Multiple Images of Large-Scale Environments (SMILE Workshop), June 1998 .

[Paper]
M. Irani, P. Anandan, and D. Weinshall, From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications . European Conference on Computer Vision (ECCV), June 1998.

[Paper]
M. Irani and P. Anandan, Video Indexing Based on Mosaic Representations. Proceedings of IEEE, May 1998.

[Paper]
M. Irani and P. Anandan, 1997. A Unified Approach to Moving Object Detection in 2D and 3D Scenes . IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), June 1998.

[Paper]
M. Irani and P. Anandan, Robust Multi-Sensor Image Alignment . IEEE International Conference on Computer Vision (ICCV), India, January 1998.

[Paper]
Irani, M; Sawhney, HS; Kumar, R; Anandan, P (1997). Interactive content-based video indexing and browsing. 1997 Ieee First Workshop On Multimedia Signal Processing. 313-318.

[Paper]
Irani, M; Rousso, B; Peleg, S. Recovery of Ego-Motion Using Region Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence. 19:268-272.

[Paper]
M. Irani, P. Anandan: A unified approach to moving object detection in 2D and 3D scenes. ICPR 1996: 712-717

[Paper]
M. Irani, P. Anandan, J. Bergen, R. Kumar, and S. Hsu, Efficient Representations of Video Sequences and Their Applications . Signal Processing: Image Communication, special issue on Image and Video Semantics: Processing, Analysis, and Application, Vol. 8, No. 4, May 1996.

[Paper]
M. Irani and P. Anandan, Parallax Geometry of Pairs of Points for 3D Scene Analysis . European Conference on Computer Vision (ECCV), April 1996.

[Paper]
P. Anandan, M. Irani, R. Kumar, James R. Bergen: Video as an image data source: efficient representations and applications. ICIP 1995: 318-321
M. Irani, P. Anandan, Steven C. Hsu: Mosaic Based Representations of Video Sequences and Their Applications. ICCV 1995: 605-611

[Paper]
M. Irani, S. Hsu, and P. Anandan, Video Compression Using Mosaic Representations . Signal Processing: Image Communication, special issue on Coding Techniques for Low Bit-rate Video, Vol. 7, No. 4-6, pp. 529-552, November 1995.

(Paper pages & Figure pages)
M. Irani, B. Rousso, S. Peleg: Recovery of ego-motion using image stabilization. CVPR 1994: 454-460

[Paper]
M. Irani, B. Rousso, and S. Peleg, Computing Occluding and Transparent Motions . International Journal of Computer Vision (IJCV), Vol. 12, No. 1, pp. 5-16, February 1994.

[Paper]
M. Irani, B. Rousso, S. Peleg: Robust Recovery of Ego-Motion. CAIP 1993: 371-378

[Paper]
M. Irani and S. Peleg, Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency . Journal of Visual Communication and Image Representation, Vol. 4, No. 4, pp. 324-335, December 1993.

[Paper]
Michal Irani, Shmuel Peleg: Image sequence enhancement using multiple motions analysis. CVPR 1992: 216-221

[Paper]
M. Irani, B. Rousso, S. Peleg: Detecting and Tracking Multiple Moving Objects Using Temporal Integration. ECCV 1992: 282-287

[Paper]
M. Irani and S. Peleg, Improving Resolution by Image Registration . CVGIP: Graphical Models and Image Processing, Vol. 53, pp. 231-239, May 1991.

[Paper]