3 papers
cs.CV2026
HELIOS: From midnight to noon, continuous outdoor urban scene relighting
Hala Djeghim, Nathan Piasco, Luis Roldão +4
Modifying the illumination of driving images is a fundamental challenge, as most datasets are captured at specific times of day. Existing methods rely on synthetic data or paired m…
cs.CV2025
SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model
Hala Djeghim, Nathan Piasco, Luis Roldão +4
Intrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream app…
cs.CV2025
J-NeuS: Joint field optimization for Neural Surface reconstruction in urban scenes with limited image overlap
Fusang Wang, Hala Djeghim, Nathan Piasco +6
Reconstructing the surrounding surface geometry from recorded driving sequences poses a significant challenge due to the limited image overlap and complex topology of urban environ…