改进视觉Transformer的视频插帧方法

针对现有的视频插帧方法无法有效处理大运动和复杂运动场景的问题，提出了一种改进视觉Transformer的视频插帧方法。该方法融合了基于跨尺度窗口的注意力和可分离的时空局部注意力，增大了注意力的感受野并聚合了多尺度信息；对时空依赖和远程像素依赖关系进行联合建模，进而增强了模型对大运动场景的处理能力。实验结果表明，该方法在Vimeo90K测试集和DAVIS数据集上的PSNR指标分别达到了37.13 dB和28.28 dB,SSIM指标分别达到了0.978和0.891。同时，可视化结果表明，该方法针对存在大运动、复杂运动和遮挡场景的视频能产生清晰合理的插帧结果。

Video frame interpolation method based on improved visual Transformer

Aiming at the problem that the existing video frame interpolation methods cannot effectively deal with large motion and complex motion scenes, this paper proposed a video frame interpolation method based on improved vision Transformer. This method fused the cross-scale window-based attention and the separable spatial-temporal local attention, enlarged the receptive field of attention, and aggregated multi-scale information. It jointly modeled the spatial-temporal dependencies and long-range pixel dependencies, thereby enhancing the model''s ability to handle large motion scenes. The experimental results show that this model achieves PSNR values of 37.13 dB and 28.28 dB on the Vimeo90K test set and the DAVIS dataset, respectively, while the SSIM values reach 0.978 and 0.891, respectively. At the same time, visualization results show that the proposed method can produce clear and reasonable frame interpolation results for videos with large motion, complex motion and occlusion scenes.