15 papers
EditSSC: Toward Editable Semantic Occupancy Scenes with Unconditional Diffusion Models
Fatima Balde, Raoul de Charette, Alexandre Boulch
3D semantic scene generation is crucial for autonomous driving applications, yet most methods rely on complex 3D-specific architectures such as triplane encoders and adapted diffus…
Exploring Easy Boosts for Lidar Semantic Scene Completion
Tetiana Martyniuk, Jonathan Seele, Alexandre Boulch +3
This paper investigates "free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns. We first demons…
NewtPhys: Do Foundation Models Understand Newtonian Physics?
Sebastian Cavada, Soumava Paul, Tuan-Hung Vu +2
Previous work has evaluated physics reasoning in foundation models using synthetic or semi-synthetic scenes and visual question-answering tasks. However, these benchmarks emphasize…
Domain Adaptation with a Single Vision-Language Embedding
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc +2
Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in real-wor…
StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
Anh-Quan Cao, Ivan Lopes, Raoul de Charette
Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Levera…
CLIP's Visual Embedding Projector is a Few-shot Cornucopia
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc +2
We introduce ProLIP, a simple and architecture-agnostic method for adapting contrastively pretrained vision-language models, such as CLIP, to few-shot classification. ProLIP fine-t…