2 papers
cs.CV2025
xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion
Saad Lahlali, Sandra Kara, Hejer Ammar +4
Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing int…
cs.CV2024
GaussianBeV: 3D Gaussian Representation meets Perception Models for BeV Segmentation
Florian Chabot, Nicolas Granger, Guillaume Lapouge
The Bird's-eye View (BeV) representation is widely used for 3D perception from multi-view camera images. It allows to merge features from different cameras into a common space, pro…