collaborators

6 papers

cs.CV2026

Style-Based Neural Architectures for Real-Time Weather Classification

Hamed Ouattara, Pascal Houssam Salmane, Pierre Duthon +2

In this paper, we present three neural network architectures designed for real-time classification of weather conditions (sunny, rain, snow, fog) from images. These models, inspire…

cs.CV2026

Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance

Hamed Ouattara, Pierre Duthon, Pascal Houssam Salmane +2

One of the dominant paradigms in self-supervised learning (SSL), illustrated by MoCo or DINO, aims to produce robust representations by capturing features that are insensitive to c…

cs.CV2026

Heuristic Style Transfer for Real-Time, Efficient Weather Attribute Detection

Hamed Ouattara, Pierre Duthon, Pascal Houssam Salmane +2

We present lightweight and efficient architectures to detect weather conditions from RGB images, predicting the weather type (sunny, rain, snow, fog) and 11 complementary attribute…

cs.CV2025

StixelNExT++: Lightweight Monocular Scene Segmentation and Representation for Collective Perception

Marcel Vosshans, Omar Ait-Aider, Youcef Mezouar +1

This paper presents StixelNExT++, a novel approach to scene representation for monocular perception systems. Building on the established Stixel representation, our method infers 3D…

cs.CV2025

StixelNExT: Toward Monocular Low-Weight Perception for Object Segmentation and Free Space Detection

Marcel Vosshans, Omar Ait-Aider, Youcef Mezouar +1

In this work, we present a novel approach for general object segmentation from a monocular image, eliminating the need for manually labeled training data and enabling rapid, straig…

cs.RO2025

CoopScenes: Multi-Scene Infrastructure and Vehicle Data for Advancing Collective Perception in Autonomous Driving

Marcel Vosshans, Alexander Baumann, Matthias Drueppel +4

The increasing complexity of urban environments has underscored the potential of effective collective perception systems. To address these challenges, we present the CoopScenes dat…