Mohamed Chaouch — accepted AI-conference papers

2026

Improving Controllable Generation: Faster Training and Better Performance via x0-Supervision

Amadou S. Sangare, Adrien Maglo, Mohamed Chaouch, Bertrand Luvison

CVPR 2026

Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language alone cannot reliably express. Controllable generation methods

Cited by 0 Source ↗code ↗Scholar ↗

2017

Deep MANTA: A Coarse-To-Fine Many-Task Network for Joint 2D and 3D Vehicle Analysis From Monocular Image

Florian Chabot, Mohamed Chaouch, Jaonary Rabarisoa, Celine Teuliere, Thierry Chateau

CVPR 2017poster

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part localization, visibility characterization and 3D dimension estimation. Its archite…

Cited by 564 PDF ↗Scholar ↗