11 papers
Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data
Thang-Anh-Quan Nguyen, Moussab Bennehar, Luis Guillermo Roldao Jimenez +5
Reliable perception under diverse weather conditions remains a major challenge for autonomous driving systems. A common strategy to improve robustness is either to synthesize adver…
A Transport-Based Geometry of Belief-Cost
Laurent Caraffa
A finite agent, a machine's digital twin or any bounded reasoner, infers a fixed and noisy world through finite sensors, so its coherent output is a belief: a probability density o…
SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
Hiba Dahmani, Nathan Piasco, Moussab Bennehar +5
Scalable generation of outdoor driving scenes requires 3D representations that remain consistent across multiple viewpoints and scale to large areas. Existing solutions either rely…
Dissipative Learning: A Framework for Viable Adaptive Systems
Laurent Caraffa
We propose a perspective in which learning is an intrinsically dissipative process. Forgetting and regularization are not heuristic add-ons but structural requirements for adaptive…
Thermodynamically Optimal Regularization under Information-Geometric Constraints
Laurent Caraffa
Modern machine learning relies on a collection of empirically successful but theoretically heterogeneous regularization techniques, such as weight decay, dropout, and exponential m…
BEDS : Bayesian Emergent Dissipative Structures : A Formal Framework for Continuous Inference Under Energy Constraints
Laurent Caraffa
We introduce BEDS (Bayesian Emergent Dissipative Structures), a formal framework for analyzing inference systems that must maintain beliefs continuously under energy constraints. U…
Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis
Thang-Anh-Quan Nguyen, Nathan Piasco, Luis Roldão +5
Synthesizing extrapolated views remains a difficult task, especially in urban driving scenes, where the only reliable sources of data are limited RGB captures and sparse LiDAR poin…
Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?
Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi +5
Tri-Planar NeRFs enable the application of powerful 2D vision models for 3D tasks, by representing 3D objects using 2D planar structures. This has made them the prevailing choice t…
Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi +5
While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides red…
Exploring 3D-aware Latent Spaces for Efficiently Learning Numerous Scenes
Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi +5
We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory…
RefinedFields: Radiance Fields Refinement for Planar Scene Representations
Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi +3
Planar scene representations have recently witnessed increased interests for modeling scenes from images, as their lightweight planar structure enables compatibility with image-bas…