3D View Optimization for
Improving Image Aesthetics

Taichi Uchida, Yoshihiro Kanamori, Yuki Endo
University of Tsukuba
ICASSP 2025
Paper arXiv
Banner image

Overview of our method. The input image is first extrapolated in the pre-processing and then fed to a 3D reconstruction method [Shih et al., 2020] to obtain a point cloud that represents the 3D scene. Our method optimizes camera parameters to maximize the aesthetic score [Wei et al., 2018] of the rendered image.

Abstract

Achieving aesthetically pleasing photography necessitates attention to multiple factors, including composition and capture conditions, which pose challenges to novices. Prior research has explored the enhancement of photo aesthetics post-capture through 2D manipulation techniques; however, these approaches offer limited search space for aesthetics. We introduce a pioneering method that employs 3D operations to simulate the conditions at the moment of capture retrospectively. Our approach extrapolates the input image and then reconstructs the 3D scene from the extrapolated image, followed by optimization to find camera parameters and image size that yield the best 3D view with enhanced aesthetics. Comparative qualitative and quantitative assessments reveal that our method surpasses traditional 2D editing techniques with superior aesthetics.

BibTeX


        @inproceedings{UchidaICASSP2025,
          author = {Taichi Uchida and Yoshihiro Kanamori and Yuki Endo},
          title={{3D} View Optimization for Improving Image Aesthetics},
          booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
          year={2025}
        }