FewarNet: An efficient few-shot view synthesis network based on trend regularization

This paper presents FewarNet, an efficient few-shot view synthesis network that leverages trend regularization techniques to improve the quality of novel view generation from limited input viewpoints. The method addresses the challenging problem of sparse-view multi-view synthesis, which is crucial for various applications in 3D computer vision and computer graphics.

Recommended citation: C Song, S Wang, J Wei, Y Zhao. (2024). "FewarNet: An efficient few-shot view synthesis network based on trend regularization." IEEE Transactions on Circuits and Systems for Video Technology. 34 (10), 9264-9278.
Download Paper