Dual-Camera Smooth Zoom on Mobile Phones
This addresses the user experience issue of smooth zooming on mobile phones, but it is incremental as it builds on existing frame interpolation techniques with a novel data generation approach.
The paper tackles the problem of noticeable jumps in geometric content and image color during zooming between dual cameras on mobile phones, introducing a new task called dual-camera smooth zoom (DCSZ) and proposing a data factory solution using virtual cameras and a novel ZoomGS method to generate synthetic data, which fine-tunes frame interpolation models and achieves significant performance improvement over original ones.
When zooming between dual cameras on a mobile, noticeable jumps in geometric content and image color occur in the preview, inevitably affecting the user's zoom experience. In this work, we introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview. The frame interpolation (FI) technique is a potential solution but struggles with ground-truth collection. To address the issue, we suggest a data factory solution where continuous virtual cameras are assembled to generate DCSZ data by rendering reconstructed 3D models of the scene. In particular, we propose a novel dual-camera smooth zoom Gaussian Splatting (ZoomGS), where a camera-specific encoding is introduced to construct a specific 3D model for each virtual camera. With the proposed data factory, we construct a synthetic dataset for DCSZ, and we utilize it to fine-tune FI models. In addition, we collect real-world dual-zoom images without ground-truth for evaluation. Extensive experiments are conducted with multiple FI methods. The results show that the fine-tuned FI models achieve a significant performance improvement over the original ones on DCSZ task. The datasets, codes, and pre-trained models will are available at https://github.com/ZcsrenlongZ/ZoomGS.