Iro Laina

86 papers A* 19A 3Journal 50Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
Do 3D Large Language Models Really Understand 3D Spatial Relationships?
CoRR
Xianzheng Ma, Tao Sun, Shuai Chen, Yash Bhalgat, Jindong Gu, Angel X. Chang, Iro Armeni, Iro Laina, Songyou Peng, Victor Adrian Prisacariu
2026 J jnl
Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video.
CoRR
Zeren Jiang, Chuanxia Zheng, Iro Laina, Diane Larlus, Andrea Vedaldi
2025 J jnl
AnimalClue: Recognizing Animals by their Traces.
CoRR
Risa Shinoda, Nakamasa Inoue, Iro Laina, Christian Rupprecht, Hirokatsu Kataoka
2025 J jnl
AutoPartGen: Autogressive 3D Part Generation and Discovery.
CoRR
Minghao Chen, Jianyuan Wang, Roman Shapovalov, Tom Monnier, Hyunyoung Jung, Dilin Wang, Rakesh Ranjan, Iro Laina, Andrea Vedaldi
2025 J jnl
Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction.
CoRR
Zeren Jiang, Chuanxia Zheng, Iro Laina, Diane Larlus, Andrea Vedaldi
2025 — conf
Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting.
3DV
Paul Engstler, Andrea Vedaldi, Iro Laina, Christian Rupprecht
2025 A* conf
Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos.
CVPR
Vadim Tschernezki, Diane Larlus, Iro Laina, Andrea Vedaldi
2025 J jnl
Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos.
CoRR
Vadim Tschernezki, Diane Larlus, Iro Laina, Andrea Vedaldi
2025 J jnl
Learning segmentation from point trajectories.
CoRR
Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2025 A* conf
PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models.
CVPR
Minghao Chen, Roman Shapovalov, Iro Laina, Tom Monnier, Jianyuan Wang, David Novotný, Andrea Vedaldi
2025 J jnl
Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections.
CoRR
Jing Wu, Zirui Wang, Iro Laina, Victor Adrian Prisacariu
2025 J jnl
SynCity: Training-Free Generation of 3D Worlds.
CoRR
Paul Engstler, Aleksandar Shtedritski, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2025 J jnl
TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility.
CoRR
Saman Motamed, Minghao Chen, Luc Van Gool, Iro Laina
2025 J jnl
What Happens Next? Anticipating Future Motion by Generating Point Trajectories.
CoRR
Gabrijel Boduljak, Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2024 — conf
3D-Aware Instance Segmentation and Tracking in Egocentric Videos.
ACCV (3)
Yash Bhalgat, Vadim Tschernezki, Iro Laina, João F. Henriques, Andrea Vedaldi, Andrew Zisserman
2024 J jnl
3D-Aware Instance Segmentation and Tracking in Egocentric Videos.
CoRR
Yash Bhalgat, Vadim Tschernezki, Iro Laina, João F. Henriques, Andrea Vedaldi, Andrew Zisserman
2024 — conf
DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing.
ECCV (74)
Minghao Chen, Iro Laina, Andrea Vedaldi
2024 J jnl
DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing.
CoRR
Minghao Chen, Iro Laina, Andrea Vedaldi
2024 — conf
Diffusion Models for Open-Vocabulary Segmentation.
ECCV (5)
Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
2024 A* conf
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation.
ICML
Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Natalia Neverova, Andrea Vedaldi, Oran Gafni, Filippos Kokkinos
2024 J jnl
IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation.
CoRR
Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Natalia Neverova, Andrea Vedaldi, Oran Gafni, Filippos Kokkinos
2024 J jnl
Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting.
CoRR
Paul Engstler, Andrea Vedaldi, Iro Laina, Christian Rupprecht
2024 A* conf
Learning Segmentation from Point Trajectories.
NeurIPS
Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2024 — conf
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields.
ECCV (59)
Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi
2024 J jnl
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields.
CoRR
Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi
2024 J jnl
PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models.
CoRR
Minghao Chen, Roman Shapovalov, Iro Laina, Tom Monnier, Jianyuan Wang, David Novotný, Andrea Vedaldi
2024 — conf
Rethinking Image Super-Resolution from Training Data Perspectives.
ECCV (17)
Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki
2024 J jnl
Rethinking Image Super-Resolution from Training Data Perspectives.
CoRR
Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki
2024 — conf
Scaling Backwards: Minimal Synthetic Pre-Training?
ECCV (15)
Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka
2024 J jnl
Scaling Backwards: Minimal Synthetic Pre-training?
CoRR
Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka
2024 A* conf
Shap-Editor: Instruction-guided Latent 3D Editing in Seconds.
CVPR
Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
2024 J jnl
Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs.
CoRR
Brandon Smart, Chuanxia Zheng, Iro Laina, Victor Adrian Prisacariu
2024 J jnl
The Curious Layperson: Fine-Grained Image Recognition Without Expert Labels.
Int. J. Comput. Vis.
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2024 A conf
Training-Free Layout Control with Cross-Attention Guidance.
WACV
Minghao Chen, Iro Laina, Andrea Vedaldi
2024 J jnl
When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models.
CoRR
Xianzheng Ma, Yash Bhalgat, Brandon Smart, Shuai Chen, Xinghui Li, Jian Ding, Jindong Gu, Dave Zhenyu Chen, Songyou Peng, Jia-Wang Bian, Philip H. S. Torr, Marc Pollefeys, Matthias Nießner, Ian D. Reid, Angel X. Chang, Iro Laina, Victor Adrian Prisacariu
2023 A* conf
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion.
NeurIPS
Yash Bhalgat, Iro Laina, João F. Henriques, Andrea Vedaldi, Andrew Zisserman
2023 J jnl
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion.
CoRR
Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi
2023 J jnl
Diffusion Models for Zero-Shot Open-Vocabulary Segmentation.
CoRR
Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
2023 A* conf
EPIC Fields: Marrying 3D Geometry and Video Understanding.
NeurIPS
Vadim Tschernezki, Ahmad Darkhalil, Zhifan Zhu, David Fouhey, Iro Laina, Diane Larlus, Dima Damen, Andrea Vedaldi
2023 J jnl
EPIC Fields: Marrying 3D Geometry and Video Understanding.
CoRR
Vadim Tschernezki, Ahmad Darkhalil, Zhifan Zhu, David Fouhey, Iro Laina, Diane Larlus, Dima Damen, Andrea Vedaldi
2023 A* conf
RealFusion 360° Reconstruction of Any Object from a Single Image.
CVPR
Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2023 J jnl
RealFusion: 360° Reconstruction of Any Object from a Single Image.
CoRR
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
2023 J jnl
SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds.
CoRR
Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
2023 J jnl
Training-Free Layout Control with Cross-Attention Guidance.
CoRR
Minghao Chen, Iro Laina, Andrea Vedaldi
2023 J jnl
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation.
CoRR
Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina
2022 A* conf
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization.
CVPR
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
2022 J jnl
Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization.
CoRR
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
2022 A* conf
Finding an Unsupervised Image Segmenter in each of your Deep Generative Models.
ICLR
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
2022 A conf
Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion.
BMVC
Subhabrata Choudhury, Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
2022 J jnl
Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion.
CoRR
Subhabrata Choudhury, Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
2022 J jnl
Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing.
CoRR
Iro Laina, Yuki M. Asano, Andrea Vedaldi
2022 A* conf
Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing.
ICLR
Iro Laina, Yuki M. Asano, Andrea Vedaldi
2022 — conf
Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations.
3DV
Vadim Tschernezki, Iro Laina, Diane Larlus, Andrea Vedaldi
2022 J jnl
Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations.
CoRR
Vadim Tschernezki, Iro Laina, Diane Larlus, Andrea Vedaldi
2022 A* conf
Unsupervised Multi-Object Segmentation by Predicting Probable Motion Patterns.
NeurIPS
Laurynas Karazija, Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2022 J jnl
Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns.
CoRR
Laurynas Karazija, Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2021 — conf
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation.
NeurIPS Datasets and Benchmarks
Laurynas Karazija, Iro Laina, Christian Rupprecht
2021 J jnl
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation.
CoRR
Laurynas Karazija, Iro Laina, Christian Rupprecht
2021 J jnl
Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models.
CoRR
Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
2021 A conf
The Curious Layperson: Fine-Grained Image Recognition without Expert Labels.
BMVC
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2021 J jnl
The Curious Layperson: Fine-Grained Image Recognition without Expert Labels.
CoRR
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2021 A* conf
Unsupervised Part Discovery from Contrastive Reconstruction.
NeurIPS
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2021 J jnl
Unsupervised Part Discovery from Contrastive Reconstruction.
CoRR
Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
2020 A* conf
Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning.
NeurIPS
Iro Laina, Ruth Fong, Andrea Vedaldi
2020 J jnl
Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning.
CoRR
Iro Laina, Ruth C. Fong, Andrea Vedaldi
2020 A* conf
Semantic Image Manipulation Using Scene Graphs.
CVPR
Helisa Dhamo, Azade Farshad, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari, Christian Rupprecht
2020 J jnl
Semantic Image Manipulation Using Scene Graphs.
CoRR
Helisa Dhamo, Azade Farshad, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari, Christian Rupprecht
2020 — —
Semantics, Language and Geometry: Learning to Understand the Scene.
Iro Laina
2020 — ch.
Semantik, Sprache und Geometrie: Szenenverständnis lernen.
Ausgezeichnete Informatikdissertationen
Iro Laina
2019 J jnl
2017 Robotic Instrument Segmentation Challenge.
CoRR
Max Allan, Alexey Shvets, Thomas Kurmann, Zichen Zhang, Rahul Duggal, Yun-Hsuan Su, Nicola Rieke, Iro Laina, Niveditha Kalavakonda, Sebastian Bodenstedt, Luis C. García-Peraza, Wenqi Li, Vladimir Iglovikov, Huoling Luo, Jian Yang, Danail Stoyanov, Lena Maier-Hein, Stefanie Speidel, Mahdi Azizian
2019 J jnl
Peeking behind objects: Layered depth prediction from a single image.
Pattern Recognit. Lett.
Helisa Dhamo, Keisuke Tateno, Iro Laina, Nassir Navab, Federico Tombari
2019 A* conf
Towards Unsupervised Image Captioning With Shared Multimodal Embeddings.
ICCV
Iro Laina, Christian Rupprecht, Nassir Navab
2019 J jnl
Towards Unsupervised Image Captioning with Shared Multimodal Embeddings.
CoRR
Iro Laina, Christian Rupprecht, Nassir Navab
2018 — conf
Dealing with Ambiguity in Robotic Grasping via Multiple Predictions.
ACCV (4)
Ghazal Ghazaei, Iro Laina, Christian Rupprecht, Federico Tombari, Nassir Navab, Kianoush Nazarpour
2018 J jnl
Dealing with Ambiguity in Robotic Grasping via Multiple Predictions.
CoRR
Ghazal Ghazaei, Iro Laina, Christian Rupprecht, Federico Tombari, Nassir Navab, Kianoush Nazarpour
2018 A* conf
Guide Me: Interacting With Deep Networks.
CVPR
Christian Rupprecht, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari
2018 J jnl
Guide Me: Interacting with Deep Networks.
CoRR
Christian Rupprecht, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari
2018 J jnl
Peeking Behind Objects: Layered Depth Prediction from a Single Image.
CoRR
Helisa Dhamo, Keisuke Tateno, Iro Laina, Nassir Navab, Federico Tombari
2017 A* conf
CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction.
CVPR
Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab
2017 J jnl
CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction.
CoRR
Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab
2017 — conf
Concurrent Segmentation and Localization for Tracking of Surgical Instruments.
MICCAI (2)
Iro Laina, Nicola Rieke, Christian Rupprecht, Josué Page Vizcaíno, Abouzar Eslami, Federico Tombari, Nassir Navab
2017 J jnl
Concurrent Segmentation and Localization for Tracking of Surgical Instruments.
CoRR
Iro Laina, Nicola Rieke, Christian Rupprecht, Josué Page Vizcaíno, Abouzar Eslami, Federico Tombari, Nassir Navab
2017 A* conf
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses.
ICCV
Christian Rupprecht, Iro Laina, Robert S. DiPietro, Maximilian Baust
2016 — conf
Deeper Depth Prediction with Fully Convolutional Residual Networks.
3DV
Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab
2016 J jnl
Deeper Depth Prediction with Fully Convolutional Residual Networks.
CoRR
Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab
2016 J jnl
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses.
CoRR
Christian Rupprecht, Iro Laina, Maximilian Baust, Federico Tombari, Gregory D. Hager, Nassir Navab