A framework and dataset that constructs seasonal 3D mountain landscapes from over 85,000 sparse webcam images across 32 locations and 13 timestamps by mesh projection and conditional diffusion inpainting, enabling standard relighting.
3d reconstruction from satellite imagery using deep learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams
A framework and dataset that constructs seasonal 3D mountain landscapes from over 85,000 sparse webcam images across 32 locations and 13 timestamps by mesh projection and conditional diffusion inpainting, enabling standard relighting.