Skip to main content
Menu

Dr

Iro Laina

Departmental Lecturer in Computer Vision

Biography

Iro Laina joined the Visual Geometry Group at the University of Oxford as a PDRA in 2020 and became a Departmental Lecturer in Computer Vision in 2023. She has received her PhD (Dr. rer. nat.) from the Technical University of Munich (TUM), Germany, and her PhD dissertation has been recognized with the ECVA PhD Award. Before that, she completed a Msc in Biomedical Computing at TUM and a Diploma in Electrical and Computer Engineering at the National Technical University of Athens (NTUA).

Her research focuses on developing perception systems for understanding images, videos, and the 3D world, via unsupervised and language-supervised learning.

 

Research Interests

  • Computer Vision
  • Unsupervised, self-supervised, and language-supervised learning
  • Semantic and geometric understanding

Research Groups

IM-3D: iterative multiview diffusion and reconstruction for high-quality 3D generation

Melas-Kyriazi L, Laina I, Rupprecht C, Neverova N, Vedaldi A et al. (2024)

BibTeX View PDF
@misc{imditerativemul-2024/2,
  title={IM-3D: iterative multiview diffusion and reconstruction for high-quality 3D generation},
  author={Melas-Kyriazi L, Laina I, Rupprecht C, Neverova N, Vedaldi A et al.},
  year = "2024"
}

EPIC Fields: marrying 3D geometry and video understanding

Tschernezki V, Darkhalil A, Zhu Z, Fouhey D, Laina I et al. (2024), Proceedings of Advances in Neural Information Processing Systems (NeurIPS): Track on Datasets and Benchmarks, 2023, 36, 26485-26500

BibTeX
@inproceedings{epicfieldsmarry-2024/1,
  title={EPIC Fields: marrying 3D geometry and video understanding},
  author={Tschernezki V, Darkhalil A, Zhu Z, Fouhey D, Laina I et al.},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS2023)},
  pages={26485-26500},
  year = "2024"
}

RealFusion: 360 reconstruction of any object from a single image

Melas-Kyriazi L, Laina I, Rupprecht C & Vedaldi A (2023), 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8446-8455

BibTeX View PDF
@inproceedings{realfusionrecon-2023/8,
  title={RealFusion: 360 reconstruction of any object from a single image},
  author={Melas-Kyriazi L, Laina I, Rupprecht C & Vedaldi A},
  booktitle={Conference on Computer Vision and Pattern Recognition (CVPR 2023)},
  pages={8446-8455},
  year = "2023"
}

Neural feature fusion fields: 3D distillation of self-supervised 2D image representations

Tschernezki V, Laina I, Larlus D & Vedaldi A (2023), 2022 International Conference on 3D Vision (3DV), 443-453

BibTeX View PDF
@inproceedings{neuralfeaturefu-2023/2,
  title={Neural feature fusion fields: 3D distillation of self-supervised 2D image representations},
  author={Tschernezki V, Laina I, Larlus D & Vedaldi A},
  booktitle={10th International Conference on 3D Vision (3DV 2022)},
  pages={443-453},
  year = "2023"
}

Guess what moves: unsupervised video and image segmentation by anticipating motion

Choudhury S, Karazija L, Laina I, Vedaldi A & Rupprecht C (2022), 33rd British Machine Vision Conference Proceedings

BibTeX
@inproceedings{guesswhatmovesu-2022/11,
  title={Guess what moves: unsupervised video and image segmentation by anticipating motion},
  author={Choudhury S, Karazija L, Laina I, Vedaldi A & Rupprecht C},
  booktitle={33rd British Machine Vision Conference (BMVC 2022)},
  year = "2022"
}

Deep spectral methods: a surprisingly strong baseline for unsupervised semantic segmentation and localization

Melas-Kyriazi L, Rupprecht C, Laina I & Vedaldi A (2022), 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8354-8365

BibTeX View PDF
@inproceedings{deepspectralmet-2022/9,
  title={Deep spectral methods: a surprisingly strong baseline for unsupervised semantic segmentation and localization},
  author={Melas-Kyriazi L, Rupprecht C, Laina I & Vedaldi A},
  booktitle={IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR 2022)},
  pages={8354-8365},
  year = "2022"
}

The curious layperson: fine-grained image recognition without expert labels

Choudhury S, Laina I, Rupprecht C & Vedaldi A (2022), Proceedings of the 32nd British Machine Vision Conference (BMVC 2021)

BibTeX
@inproceedings{thecuriouslaype-2022/3,
  title={The curious layperson: fine-grained image recognition without expert labels},
  author={Choudhury S, Laina I, Rupprecht C & Vedaldi A},
  booktitle={32nd British Machine Vision Conference (BMVC 2021)},
  year = "2022"
}

Unsupervised multi-object segmentation by predicting probable motion patterns

Karazija L, Choudhury S, Laina I, Rupprecht C & Vedaldi A (2022), Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 35

BibTeX
@inproceedings{unsupervisedmul-2022/1,
  title={Unsupervised multi-object segmentation by predicting probable motion patterns},
  author={Karazija L, Choudhury S, Laina I, Rupprecht C & Vedaldi A},
  booktitle={36th Neural Information Processing Systems (NeurIPS 2022)},
  year = "2022"
}

Unsupervised part discovery from contrastive reconstruction

Choudhury S, Laina I, Rupprecht C & Vedaldi A (2021), Proceedings of the 34th Conference on Neural Information Processing Systems (NeuRIPS 2021)

BibTeX
@inproceedings{unsupervisedpar-2021/12,
  title={Unsupervised part discovery from contrastive reconstruction},
  author={Choudhury S, Laina I, Rupprecht C & Vedaldi A},
  booktitle={34th Conference on Neural Information Processing Systems (NeuRIPS 2021)},
  year = "2021"
}

Measuring the interpretability of unsupervised representations via quantized reversed probing

Laina I, Asano Y & Vedaldi A (2021), International Conference on Learning Representations

BibTeX
@inproceedings{measuringtheint-2021/9,
  title={Measuring the interpretability of unsupervised representations via quantized reversed probing},
  author={Laina I, Asano Y & Vedaldi A},
  booktitle={Tenth International Conference on Learning Representations (ICLR 2022)},
  year = "2021"
}
View all