The UAVs in Multimedia (UAVM) 2024 competition aims to improve the performance of Drone-based Geo-localization task under extreme weather. On the task, we found the simple augmentation on training set can significant improve performance with zero-cost and won the 6th Place among 22 teams on this competition. Furthermore, based on our observations, we propose a domain translation framework to further enhance the performance of any model. We transfer images from a multi-weather domain to a normal domain using GAN and introduce FFM to further reduce computational costs. Our experiments revealed that while this strategy indeed improves image quality, it does not translate into improved recognition accuracy. Thus, while our strategy is supported by experimental evidence, practical methods for achieving performance improvement remain elusive. We hope this report provides valuable insights for developers and researchers in this field.

In the field of geometric processing, mesh denoising plays an important role. Meshes obtained from 3D reconstruction often contain noise that cannot meet requirements and thus require mesh denoising as a post-processing step. Feature-preserving mesh denoising algorithms aim to remove noise while preserving features and are considered state-of-the-art in mesh denoising. However, feature-preserving mesh denoising algorithms based on sparse optimization are superior in performance but time-consuming.

This paper investigates feature-preserving mesh denoising algorithms, analyzes representative works and evaluation metrics in this direction, and focuses on the L0 method for algorithm reproduction and experimentation. An efficient optimization scheme is proposed around the L0 method, along with a parallelized implementation, to improve efficiency.

The main contributions of this paper are as follows: