About

I am a computer vision postdoctoral researcher at the University of Liège, funded by the F.R.S.-FNRS, where my work focuses on improving video-text model pretraining. I recently completed a PhD at the University of Liège under the supervision of Prof. Marc Van Droogenbroeck. My broader research focuses on semi-supervised and self-supervised learning, video representation learning, and differentiable 3D reconstruction and rendering.

My thesis, Learning With Unlabeled Data, studies learning from unlabeled data for object detection, image representation learning, and video understanding.

Selected Publications
  • Advancing Video-Text Pretraining with Multi-View Captions
    Fida Mohammad Thoker, Renaud Vandeghen, Karen Sanchez, Marc Van Droogenbroeck, and Bernard Ghanem
    † Equal contribution.
    Preprint, 2026.
  • TrackMAE: Video Representation Learning via Track Mask and Predict - CVPR 2026
    Renaud Vandeghen, Fida Mohammad Thoker, Marc Van Droogenbroeck, and Bernard Ghanem
    † Equal contribution.
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
  • MeshSplatting: Differentiable Rendering with Opaque Meshes - CVPR 2026 Oral
    Jan Held, Sanghyun Son, Renaud Vandeghen, Daniel Rebain, Matheus Gadelha, Yi Zhou, Anthony Cioppa, Ming C. Lin, Marc Van Droogenbroeck, and Andrea Tagliasacchi
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
  • Triangle Splatting for Real-Time Radiance Field Rendering - 3DV 2026
    Jan Held, Renaud Vandeghen, Adrien Deliège, Abdullah Hamdi, Daniel Rebain, Silvio Giancola, Anthony Cioppa, Andrea Vedaldi, Bernard Ghanem, Andrea Tagliasacchi, and Marc Van Droogenbroeck
    In International Conference on 3D Vision (3DV), 2026.
  • 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes - CVPR 2025 Highlight
    Jan Held, Renaud Vandeghen, Abdullah Hamdi, Adrien Deliège, Anthony Cioppa, Silvio Giancola, Andrea Vedaldi, Bernard Ghanem, and Marc Van Droogenbroeck
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
  • Efficient Image Pre-training with Siamese Cropped Masked Autoencoders - ECCV 2024
    Alexandre Eymaël, Renaud Vandeghen, Anthony Cioppa, Silvio Giancola, Bernard Ghanem, and Marc Van Droogenbroeck
    In European Conference on Computer Vision (ECCV), 2024
  • Adaptive Self-Training for Object Detection - ICCVW 2023
    Renaud Vandeghen, Gilles Louppe, and Marc Van Droogenbroeck
    In IEEE/CVF International Conference on Computer Vision Workshops (ICCV Workshops), 2023