Preprint
Sep 2026
Scaling 3D Generative Priors to Large-Scale Scene Meshes from Multi-View Images
This work introduces local context tiled generation to improve geometric continuity between neighboring regions and global appearance alignment to reduce appearance discrepancies across distant regions in a training-free framework for large-scale textured mesh generation from multi-view images.
Sangeun Lee, Wonseok Chae, Hoyoung Yoo et al.
· 0 citations