Unsupervised Perception

Información del proyecto

UNION

Identificador del acuerdo de subvención: 101001212

DOI

10.3030/101001212

Fecha de la firma de la CE 7 Diciembre 2021

Fecha de inicio 1 Enero 2022

Fecha de finalización 31 Mayo 2027

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 2 311 847,00

Aportación de la UE

€ 2 311 847,00

Coordinado por

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

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Open Research Data Pilot (1)

Data Management Plan

Publicaciones

Conference proceedings (40)

Syncity: Training-Free Generation of 3D Worlds

Autores: Paul Engstler, Aleksandar Shtedritski, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Publicado en: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Página(s) 27585-27595
Editor: IEEE
DOI: 10.1109/iccv51701.2025.02561

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

Autores: Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Publicado en: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Página(s) 6772-6783
Editor: IEEE
DOI: 10.1109/iccv51701.2025.00637

Diffusion Models for Open-Vocabulary Segmentation

Autores: Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
Publicado en: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editor: Springer

Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation

Autores: Aleksandar Shtedritski; Christian Rupprecht; Andrea Vedaldi
Publicado en: Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023
Editor: IEEE
DOI: 10.1109/iccvw60793.2023.00100

EPIC Fields: Marrying 3D Geometry and Video Understanding

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

Instant Uncertainty Calibration of NeRFs Using a Meta-calibrator

Autores: Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark
Publicado en: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editor: Springer

MagicPony: Learning Articulated 3D Animals in the Wild

Autores: Shangzhe Wu, Ruining Li, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Editor: IEEE

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

Autores: Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Publicado en: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Página(s) 13405-13415
Editor: IEEE
DOI: 10.1109/iccv51701.2025.01245

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

Autores: Minghao Chen; Roman Shapovalov; Iro Laina; Tom Monnier; Jianyuan Wang; David Novotny; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Editor: IEEE

Particulate: Feed-Forward 3D Object Articulation

Autores: Ruining Li; Yuxin Yao; Chuanxia Zheng; Christian Rupprecht; Joan Lasenby; Shangzhe Wu; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Editor: IEEE

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

Autores: Thomas Jakab; Ruining Li; Shangzhe Wu; Christian Rupprecht; Andrea Vedaldi
Publicado en: Proceedings of the International Conference on 3D Vision, 2024
Editor: 3DV

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

Autores: Zeren Jiang, Chuanxia Zheng, Iro Laina, Diane Larlus, Andrea Vedaldi
Publicado en: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Página(s) 01-14
Editor: IEEE
DOI: 10.1109/iccv51701.2025.01921

ShIC: Shape-image correspondences with no keypoint supervision

Autores: Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editor: Springer

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

Autores: Luke Melas-Kyriazi, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Editor: IEEE

Continual Detection Transformer for Incremental Object Detection

Autores: Yaoyao Liu, Bernt Schiele, Andrea Vedaldi, Christian Rupprecht
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Editor: IEEE

Online Clustered Codebook

Autores: Chuanxia Zheng, Andrea Vedaldi
Publicado en: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Editor: CVF

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

Autores: Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editor: IEEE

CoWTracker: Tracking by Warping instead of Correlation

Autores: Zihang Lai; Eldar Insafutdinov; Edgar Sucar; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Editor: IEEE

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

Autores: Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Editor: CVF

RealFusion: 360 Reconstruction of Any Object from a Single Image

Autores: Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Editor: IEEE

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

Autores: Dylan Campbell; Eldar Insafutdinov; Joao F. Henriques; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision Workshop (CVPRW), 2024
Editor: IEEE

3D-Aware Instance Segmentation and Tracking in Egocentric Videos

Autores: Yash Sanjay Bhalgat; Vadim Tschernezki; Iro Laina; Joao F. Henriques; Andrea Vedaldi; Andrew Zisserman
Publicado en: Proceedings of the Asian Conference on Computer Vision (ACCV), 2024
Editor: Springer

Learning Segmentation from Point Trajectories

Autores: Laurynas Karazija; Iro Laina; Christian Rupprecht; Andrea Vedaldi
Publicado en: Proceedings of Advances on Neural Information Processing Systems (NeurIPS), 2024
Editor: NeurIPS Foundation

N2F2: Hierarchical scene understanding with nested neural feature fields

Autores: Yash Sanjay Bhalgat, Iro Laina, Joao F. Henriques, Andrew Zisserman, Andrea Vedaldi
Publicado en: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editor: Springer

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

Autores: Paul Engstler; Andrea Vedaldi; Iro Laina; Christian Rupprecht
Publicado en: Proceedings of the IEEE Conference on 3D Vision (3DV), 2025
Editor: IEEE

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

Autores: Minghao Chen, Iro Laina, Andrea Vedaldi
Publicado en: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editor: Springer

Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns

Autores: Laurynas Karazija, Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2022
Editor: Curran

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

Autores: Yash Sanjay Bhalgat, Iro Laina, Joao F. Henriques, Andrea Vedaldi, Andrew Zisserman
Publicado en: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2023
Editor: Curran

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

Autores: Edgar Sucar, Zihang Lai, Eldar Insafutdinov, Andrea Vedaldi
Publicado en: 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 2026, Página(s) 7295-7305
Editor: IEEE
DOI: 10.1109/iccv51701.2025.00685

Training-Free Layout Control with Cross-Attention Guidance

Autores: Minghao Chen; Iro Laina; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2024
Editor: WACV

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

Autores: Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Editor: CVF

Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better

Autores: Zihang Lai; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Editor: IEEE

Mesh4D: 4D mesh reconstruction and tracking from monocular video

Autores: Zeren Jiang; Chuanxia Zheng; Iro Laina; Diane Larlus; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Editor: IEEE

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

Autores: Ben Kaye, Tomas Jakab, Shangzhe Wu, Christian Ruprecht, Andrea Vedaldi
Publicado en: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, Página(s) 6425-6435
Editor: IEEE
DOI: 10.1109/cvpr52734.2025.00602

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

Autores: Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editor: IEEE

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

Autores: Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Publicado en: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editor: Springer

V-DPM: Video reconstruction with Dynamic Point Maps

Autores: Edgar Sucar; Eldar Insafutdinov; Zihang Lai; Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Editor: IEEE

Free3D: Consistent novel view synthesis without 3D representation.

Autores: Chuanxia Zheng, Andrea Vedaldi
Publicado en: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editor: IEEE

No representation rules them all in category discovery

Autores: Sagar Vaze, Andrea Vedaldi, Andrew Zisserman
Publicado en: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2023
Editor: Curran

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

Autores: Vadim Tschernezki, Iro Laina, Diane Larlus, Andrea Vedaldi
Publicado en: Proceedings of the International Conference on 3D Vision (3DV), 2022
Editor: IEEE
DOI: 10.1109/3dv57658.2022.00056