Unsupervised Perception

Project Information

UNION

Grant agreement ID: 101001212

DOI

10.3030/101001212

EC signature date 7 December 2021

Start date 1 January 2022

End date 31 May 2027

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 2 311 847,00

EU contribution

€ 2 311 847,00

Coordinated by

THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD
United Kingdom

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Deliverables

Open Research Data Pilot (1)

Data Management Plan

Publications

Conference proceedings (40)

Syncity: Training-Free Generation of 3D Worlds

Author(s): Paul Engstler, Aleksandar Shtedritski, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Published in: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Page(s) 27585-27595
Publisher: IEEE
DOI: 10.1109/iccv51701.2025.02561

DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness

Author(s): Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Published in: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Page(s) 6772-6783
Publisher: IEEE
DOI: 10.1109/iccv51701.2025.00637

Diffusion Models for Open-Vocabulary Segmentation

Author(s): Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
Published in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Publisher: Springer

Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation

Author(s): Aleksandar Shtedritski; Christian Rupprecht; Andrea Vedaldi
Published in: Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023
Publisher: IEEE
DOI: 10.1109/iccvw60793.2023.00100

EPIC Fields: Marrying 3D Geometry and Video Understanding

Author(s): Vadim Tschernezki, Ahmad Darkhalil, Zhifan Zhu, David Fouhey, Iro Laina, Diane Larlus, Dima Damen, Andrea Vedaldi
Published in: Proceedings of Advances in Neural Information Processing Systems (NeurIPS): Track on Datasets and Benchmarks, 2023
Publisher: Curran

Instant Uncertainty Calibration of NeRFs Using a Meta-calibrator

Author(s): Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark
Published in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Publisher: Springer

MagicPony: Learning Articulated 3D Animals in the Wild

Author(s): Shangzhe Wu, Ruining Li, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Publisher: IEEE

Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics

Author(s): Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Published in: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Page(s) 13405-13415
Publisher: IEEE
DOI: 10.1109/iccv51701.2025.01245

PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models

Author(s): Minghao Chen; Roman Shapovalov; Iro Laina; Tom Monnier; Jianyuan Wang; David Novotny; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Publisher: IEEE

Particulate: Feed-Forward 3D Object Articulation

Author(s): Ruining Li; Yuxin Yao; Chuanxia Zheng; Christian Rupprecht; Joan Lasenby; Shangzhe Wu; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Publisher: IEEE

Farm3D: Learning articulated 3D animals by distilling 2D diffusion

Author(s): Thomas Jakab; Ruining Li; Shangzhe Wu; Christian Rupprecht; Andrea Vedaldi
Published in: Proceedings of the International Conference on 3D Vision, 2024
Publisher: 3DV

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

Author(s): Zeren Jiang, Chuanxia Zheng, Iro Laina, Diane Larlus, Andrea Vedaldi
Published in: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Page(s) 01-14
Publisher: IEEE
DOI: 10.1109/iccv51701.2025.01921

ShIC: Shape-image correspondences with no keypoint supervision

Author(s): Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Publisher: Springer

PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction

Author(s): Luke Melas-Kyriazi, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Publisher: IEEE

Continual Detection Transformer for Incremental Object Detection

Author(s): Yaoyao Liu, Bernt Schiele, Andrea Vedaldi, Christian Rupprecht
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Publisher: IEEE

Online Clustered Codebook

Author(s): Chuanxia Zheng, Andrea Vedaldi
Published in: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Publisher: CVF

Splatter Image: Ultra-fast single-view 3D reconstruction

Author(s): Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Publisher: IEEE

CoWTracker: Tracking by Warping instead of Correlation

Author(s): Zihang Lai; Eldar Insafutdinov; Edgar Sucar; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Publisher: IEEE

Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data (inproceedings)

Author(s): Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Publisher: CVF

RealFusion: 360 Reconstruction of Any Object from a Single Image

Author(s): Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Publisher: IEEE

Neural Fields for Co-Reconstructing 3D Objects from Incidental {2D} Data

Author(s): Dylan Campbell; Eldar Insafutdinov; Joao F. Henriques; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision Workshop (CVPRW), 2024
Publisher: IEEE

3D-Aware Instance Segmentation and Tracking in Egocentric Videos

Author(s): Yash Sanjay Bhalgat; Vadim Tschernezki; Iro Laina; Joao F. Henriques; Andrea Vedaldi; Andrew Zisserman
Published in: Proceedings of the Asian Conference on Computer Vision (ACCV), 2024
Publisher: Springer

Learning Segmentation from Point Trajectories

Author(s): Laurynas Karazija; Iro Laina; Christian Rupprecht; Andrea Vedaldi
Published in: Proceedings of Advances on Neural Information Processing Systems (NeurIPS), 2024
Publisher: NeurIPS Foundation

N2F2: Hierarchical scene understanding with nested neural feature fields

Author(s): Yash Sanjay Bhalgat, Iro Laina, Joao F. Henriques, Andrew Zisserman, Andrea Vedaldi
Published in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Publisher: Springer

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

Author(s): Paul Engstler; Andrea Vedaldi; Iro Laina; Christian Rupprecht
Published in: Proceedings of the IEEE Conference on 3D Vision (3DV), 2025
Publisher: IEEE

DGE: Direct gaussian 3D editing by consistent multi-view editing.

Author(s): Minghao Chen, Iro Laina, Andrea Vedaldi
Published in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Publisher: Springer

Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns

Author(s): Laurynas Karazija, Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2022
Publisher: Curran

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Author(s): Yash Sanjay Bhalgat, Iro Laina, Joao F. Henriques, Andrea Vedaldi, Andrew Zisserman
Published in: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2023
Publisher: Curran

Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction

Author(s): Edgar Sucar, Zihang Lai, Eldar Insafutdinov, Andrea Vedaldi
Published in: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Page(s) 7295-7305
Publisher: IEEE
DOI: 10.1109/iccv51701.2025.00685

Training-Free Layout Control with Cross-Attention Guidance

Author(s): Minghao Chen; Iro Laina; Andrea Vedaldi
Published in: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2024
Publisher: WACV

What does CLIP know about a red circle? Visual prompt engineering for VLMs

Author(s): Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Publisher: CVF

Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better

Author(s): Zihang Lai; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Publisher: IEEE

Mesh4D: 4D mesh reconstruction and tracking from monocular video

Author(s): Zeren Jiang; Chuanxia Zheng; Iro Laina; Diane Larlus; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Publisher: IEEE

DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction

Author(s): Ben Kaye, Tomas Jakab, Shangzhe Wu, Christian Ruprecht, Andrea Vedaldi
Published in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Page(s) 6425-6435
Publisher: IEEE
DOI: 10.1109/cvpr52734.2025.00602

SHAP-EDITOR: Instruction-guided latent 3D editing in seconds

Author(s): Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Publisher: IEEE

DragAPart: Learning a part-level motion prior for articulated objects

Author(s): Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Published in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Publisher: Springer

V-DPM: Video reconstruction with Dynamic Point Maps

Author(s): Edgar Sucar; Eldar Insafutdinov; Zihang Lai; Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Publisher: IEEE

Free3D: Consistent novel view synthesis without 3D representation.

Author(s): Chuanxia Zheng, Andrea Vedaldi
Published in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Publisher: IEEE

No representation rules them all in category discovery

Author(s): Sagar Vaze, Andrea Vedaldi, Andrew Zisserman
Published in: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2023
Publisher: Curran

Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representation (inproceedings)

Author(s): Vadim Tschernezki, Iro Laina, Diane Larlus, Andrea Vedaldi
Published in: Proceedings of the International Conference on 3D Vision (3DV), 2022
Publisher: IEEE
DOI: 10.1109/3dv57658.2022.00056