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

Rethinking Image Super-Resolution from Training Data Perspectives

Ohtani G, Tadokoro R, Yamada R, Asano YM, Laina I et al. (2025), 15075, 19-36

BibTeX View PDF
@misc{rethinkingimage-2025/,
  title={Rethinking Image Super-Resolution from Training Data Perspectives},
  author={Ohtani G, Tadokoro R, Yamada R, Asano YM, Laina I et al.},
  year = "2025"
}

Scaling Backwards: Minimal Synthetic Pre-Training?

Nakamura R, Tadokoro R, Yamada R, Asano YM, Laina I et al. (2025), 15073, 153-171

BibTeX View PDF
@misc{scalingbackward-2025/,
  title={Scaling Backwards: Minimal Synthetic Pre-Training?},
  author={Nakamura R, Tadokoro R, Yamada R, Asano YM, Laina I et al.},
  year = "2025"
}

N2F2: hierarchical scene understanding with nested neural feature fields

Bhalgat Y, Laina I, Henriques J, Zisserman A & Vedaldi A (2024), Computer Vision ??? ECCV 2024 18th European Conference, Milan, Italy, September 29???October 4, 2024, Proceedings, Part LIX, 197-214

BibTeX View PDF
@inproceedings{nfhierarchicals-2024/11,
  title={N2F2: hierarchical scene understanding with nested neural feature fields},
  author={Bhalgat Y, Laina I, Henriques J, Zisserman A & Vedaldi A},
  booktitle={20th European Conference on Computer Vision (ECCV 2024)},
  pages={197-214},
  year = "2024"
}

Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion

Bhalgat Y, Laina I, Henriques J, Zisserman A & Vedaldi A (2024), Advances in Neural Information Processing Systems 36, 9092

BibTeX
@inproceedings{contrastivelift-2024/10,
  title={Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion},
  author={Bhalgat Y, Laina I, Henriques J, Zisserman A & Vedaldi A},
  booktitle={37th Conference in Neural Information Processing Systems (NeurIPS 2023)},
  pages={9092},
  year = "2024"
}

Diffusion models for open-vocabulary segmentation

Karazija L, Laina I, Vedaldi A & Rupprecht C (2024), Computer Vision ??? ECCV 2024: 18th European Conference, Milan, Italy, September 29???October 4, 2024, Proceedings, Part V, 299-317

BibTeX View PDF
@inproceedings{diffusionmodels-2024/10,
  title={Diffusion models for open-vocabulary segmentation},
  author={Karazija L, Laina I, Vedaldi A & Rupprecht C},
  booktitle={20th European Conference on Computer Vision (ECCV 2024)},
  pages={299-317},
  year = "2024"
}

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

Smart B, Zheng C, Laina I & Prisacariu VA (2024)

BibTeX View PDF
@misc{splattrzeroshot-2024/8,
  title={Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs},
  author={Smart B, Zheng C, Laina I & Prisacariu VA},
  year = "2024"
}

3D-Aware Instance Segmentation and Tracking in Egocentric Videos

Bhalgat Y, Tschernezki V, Laina I, Henriques JF, Vedaldi A et al. (2024)

BibTeX View PDF
@misc{dawareinstances-2024/8,
  title={3D-Aware Instance Segmentation and Tracking in Egocentric Videos},
  author={Bhalgat Y, Tschernezki V, Laina I, Henriques JF, Vedaldi A et al.},
  year = "2024"
}

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models

Ma X, Bhalgat Y, Smart B, Chen S, Li X et al. (2024)

BibTeX View PDF
@misc{whenllmsstepint-2024/5,
  title={When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models},
  author={Ma X, Bhalgat Y, Smart B, Chen S, Li X et al.},
  year = "2024"
}

Training-free layout control with cross-attention guidance

Chen M, Laina I & Vedaldi A (2024), 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 5331-5341

BibTeX View PDF
@inproceedings{trainingfreelay-2024/4,
  title={Training-free layout control with cross-attention guidance},
  author={Chen M, Laina I & Vedaldi A},
  booktitle={IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024)},
  pages={5331-5341},
  year = "2024"
}

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

Engstler P, Vedaldi A, Laina I & Rupprecht C (2024)

BibTeX
@misc{invisiblestitch-2024/4,
  title={Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting},
  author={Engstler P, Vedaldi A, Laina I & Rupprecht C},
  year = "2024"
}
View all