3 papers
cs.CV2026
Synthetic Dataset Generation for Partially Observed Indoor Objects
Jelle Vermandere, Maarten Bassier, Maarten Vergauwen
Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquir…
cs.CV2026
Adaptive Scaling with Geometric and Visual Continuity of completed 3D objects
Jelle Vermandere, Maarten Bassier, Maarten Vergauwen
Object completion networks typically produce static Signed Distance Fields (SDFs) that faithfully reconstruct geometry but cannot be rescaled or deformed without introducing struct…
cs.CV2024
Semantic UV mapping to improve texture inpainting for indoor scenes
Jelle Vermandere, Maarten Bassier, Maarten Vergauwen
This work aims to improve texture inpainting after clutter removal in scanned indoor meshes. This is achieved with a new UV mapping pre-processing step which leverages semantic inf…