IDLab-MEDIA

IDLab-MEDIA

Our research team (part of Ghent University and imec) focuses on the representation, processing, compression and interactive delivery of emerging visual media formats.

Mesh-Driven 3D Gaussian Splat Manipulation

Mesh-Driven 3D Gaussian Splat Manipulation

Mesh-Driven 3D Gaussian Splat Manipulation was accepted at I3D Companion 2026.

POTR - Post-Training 3DGS Compression

POTR - Post-Training 3DGS Compression

POTR (Post-Training 3DGS Compression) was accepted at IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

TGIF2 - Extended Text-Guided Inpainting Forgery Dataset and Benchmark

TGIF2 - Extended Text-Guided Inpainting Forgery Dataset and Benchmark

TGIF2 - Extended Text-Guided Inpainting Forgery Dataset and Benchmark was accepted at Journal on Information Security.

PhD - Efficient Techniques for Light Field Rendering Featured

PhD - Efficient Techniques for Light Field Rendering

PhD - From Images to Immersion: Efficient Techniques for Light Field Rendering

WACV26 - Ignoring the Decoy

WACV26 - Ignoring the Decoy

Our paper titled "Ignoring the Decoy - A Novel Approach for Robust Image Forensics" was accepted at the SynRDinBAS workshop at WACV 2026

How AI-based Regeneration Reshapes Multimedia Forensics - WACV26 Keynote

How AI-based Regeneration Reshapes Multimedia Forensics - WACV26 Keynote

Generative Anchored Fields: Controlled Data Generation via Emergent Velocity Fields and Transport Algebra

Generative Anchored Fields: Controlled Data Generation via Emergent Velocity Fields and Transport Algebra

We present Generative Anchored Fields (GAF), a generative model that learns independent endpoint predictors, J (noise) and K (data), from any point on a linear bridge.