5 papers
SENSE: Stereo OpEN Vocabulary SEmantic Segmentation
Thomas Campagnolo, Ezio Malis, Philippe Martinet +1
Open-vocabulary semantic segmentation enables models to segment objects or image regions beyond fixed class sets, offering flexibility in dynamic environments. However, existing me…
Efficient closed-form approaches for pose estimation using Sylvester forms
Jana VráblÃková, Ezio Malis, Laurent Busé
Solving non-linear least-squares problem for pose estimation (rotation and translation) is often a time consuming yet fundamental problem in several real-time computer vision appli…
PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset
Thomas Campagnolo, Ezio Malis, Philippe Martinet +1
Understanding how natural language phrases correspond to specific regions in images is a key challenge in multimodal semantic segmentation. Recent advances in phrase grounding are…
Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration
Katie Z Luo, Minh-Quan Dao, Zhenzhen Liu +9
Vehicle-to-everything (V2X) collaborative perception has emerged as a promising solution to address the limitations of single-vehicle perception systems. However, existing V2X data…
Enhanced 3D Object Detection via Diverse Feature Representations of 4D Radar Tensor
Seung-Hyun Song, Dong-Hee Paek, Minh-Quan Dao +2
Recent advances in automotive four-dimensional (4D) Radar have enabled access to raw 4D Radar Tensor (4DRT), offering richer spatial and Doppler information than conventional point…