Unsupervised Perception

Informazioni relative al progetto

UNION

ID dell’accordo di sovvenzione: 101001212

DOI

10.3030/101001212

Data della firma CE 7 Dicembre 2021

Data di avvio 1 Gennaio 2022

Data di completamento 31 Maggio 2027

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 2 311 847,00

Contributo UE

€ 2 311 847,00

Coordinato da

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

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Open Research Data Pilot (1)

Data Management Plan

Pubblicazioni

Conference proceedings (30)

Diffusion Models for Open-Vocabulary Segmentation

Autori: Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
Pubblicato in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editore: Springer

Learning Universal Semantic Correspondences with No Supervision and Automatic Data Curation

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

EPIC Fields: Marrying 3D Geometry and Video Understanding

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

Instant Uncertainty Calibration of NeRFs Using a Meta-calibrator

Autori: Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark
Pubblicato in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editore: Springer

MagicPony: Learning Articulated 3D Animals in the Wild

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

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

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

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

Autori: Thomas Jakab; Ruining Li; Shangzhe Wu; Christian Rupprecht; Andrea Vedaldi
Pubblicato in: Proceedings of the International Conference on 3D Vision, 2024
Editore: 3DV

ShIC: Shape-image correspondences with no keypoint supervision

Autori: Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editore: Springer

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

Autori: Luke Melas-Kyriazi, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Editore: IEEE

Continual Detection Transformer for Incremental Object Detection

Autori: Yaoyao Liu, Bernt Schiele, Andrea Vedaldi, Christian Rupprecht
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Editore: IEEE

Online Clustered Codebook

Autori: Chuanxia Zheng, Andrea Vedaldi
Pubblicato in: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Editore: CVF

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

Autori: Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editore: IEEE

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

Autori: Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Editore: CVF

RealFusion: 360 Reconstruction of Any Object from a Single Image

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

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

Autori: Dylan Campbell; Eldar Insafutdinov; Joao F. Henriques; Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision Workshop (CVPRW), 2024
Editore: IEEE

3D-Aware Instance Segmentation and Tracking in Egocentric Videos

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

Learning Segmentation from Point Trajectories

Autori: Laurynas Karazija; Iro Laina; Christian Rupprecht; Andrea Vedaldi
Pubblicato in: Proceedings of Advances on Neural Information Processing Systems (NeurIPS), 2024
Editore: NeurIPS Foundation

N2F2: Hierarchical scene understanding with nested neural feature fields

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

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

Autori: Paul Engstler; Andrea Vedaldi; Iro Laina; Christian Rupprecht
Pubblicato in: Proceedings of the IEEE Conference on 3D Vision (3DV), 2025
Editore: IEEE

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

Autori: Minghao Chen, Iro Laina, Andrea Vedaldi
Pubblicato in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editore: Springer

Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns

Autori: Laurynas Karazija, Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2022
Editore: Curran

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

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

Training-Free Layout Control with Cross-Attention Guidance

Autori: Minghao Chen; Iro Laina; Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2024
Editore: WACV

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

Autori: Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of the International Conference on Computer Vision (ICCV), 2023
Editore: CVF

Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better

Autori: Zihang Lai; Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Editore: IEEE

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

Autori: Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editore: IEEE

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

Autori: Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of the European Conference on Computer Vision (ECCV), 2024
Editore: Springer

Free3D: Consistent novel view synthesis without 3D representation.

Autori: Chuanxia Zheng, Andrea Vedaldi
Pubblicato in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Editore: IEEE

No representation rules them all in category discovery

Autori: Aleksandar Shtedritski, Christian Rupprecht, Andrea Vedaldi
Pubblicato in: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), 2023
Editore: Curran

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

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