activity
20242026
collaborators

6 papers

cs.CV2026

TrackMAE: Video Representation Learning via Track Mask and Predict

Renaud Vandeghen, Fida Mohammad Thoker, Marc Van Droogenbroeck +1

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temp…

cs.CV2025

MeshSplatting: Differentiable Rendering with Opaque Meshes

Jan Held, Sanghyun Son, Renaud Vandeghen +7

Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain in…

cs.CV2025

Triangle Splatting+: Differentiable Rendering with Opaque Triangles

Jan Held, Renaud Vandeghen, Sanghyun Son +6

Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can ac…

cs.CV2025

Triangle Splatting for Real-Time Radiance Field Rendering

Jan Held, Renaud Vandeghen, Adrien Deliege +7

The field of computer graphics was revolutionized by models such as Neural Radiance Fields and 3D Gaussian Splatting, displacing triangles as the dominant representation for photog…

cs.CV2024

Physically Interpretable Probabilistic Domain Characterization

Anaïs Halin, Sébastien Piérard, Renaud Vandeghen +10

Characterizing domains is essential for models analyzing dynamic environments, as it allows them to adapt to evolving conditions or to hand the task over to backup systems when fac…

cs.CV2024

3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes

Jan Held, Renaud Vandeghen, Abdullah Hamdi +6

Recent advances in radiance field reconstruction, such as 3D Gaussian Splatting (3DGS), have achieved high-quality novel view synthesis and fast rendering by representing scenes wi…