Junheum Park

Hi, ysj-xuanyuan. In README, you can download the pre-trained checkpoints by clicking the blue '[pre-trained model](https://drive.google.com/u/0/uc?export=download&confirm=JG-C&id=1YIxJguzgFp0t7iLHw1bKLrv7JQrc4lMG)' word. Also, I attach the download link in the above 'pre-trained model' word.

Hi, l1haodong. Sorry to late answer. we will upload train codes and datasets later. If you want to use train codes as soon as possible, we recommend re-implement train codes....

Hi, 972461099. 1. What is the training set of Bilateral motion estimation? - As mentioned in the paper, we use the 'train set of Vimeo90K' dataset to train the bilateral...

Hi, thanks for your interest @qianqianwang68, @marianobasti. We designed ABME can generate an intermediate frame at arbitrary time t with some modification in the time instance. However, the provided model...

Hi, Thanks for your interest in our method. In the [paperswithcode](https://paperswithcode.com/task/video-frame-interpolation), you can find the quantitative comparison with SoftSplat and RIFE. It would be good to run the source code...

Hi, @JerryLeolfl. SBM_ is the symmetric bilateral motion vector field from t to 1. Under the linear motion assumption, we developed the bilateral cost volume layer, which computes matching costs...

Hi, Could you please post the GCC version? The minimum recommended GCC compiler is at least GCC 6 due to C++11 requirements in CUDA-11.0 libraries. We only tested on Ubuntu...

Hi, Heroandzhang. To get the error maps for comparing a test frame and target frame, you first pixel-wise subtract two frames and compute the pixel-wise absolute value of the subtraction...