Shangchen Zhou

Hi, Compared with the image domain, vgg feature domain is still more robust for patching matching in GraphAgg*. In addition, the non-learning version GraphAgg* is heavily affected by the degree...

Hi, Sorry, we didn't test our code on the Windows system. Please try to change your compiler from Visual Studio to MinGW GCC. And check out your PyTorch version should...

@ Yuliang-Zou Thanks for your reply, My input size is 320*448 that just as the Flownet ICCV15 paper's setting and I load the image by dataloader that load the batch...

Thanks for your explanation@TomoshibiAkira. How do you set the temperature_scheduler_config?

Thanks, @TomoshibiAkira. Where could I find GumbelVQ's model.yaml? I didn't see this config file in this repo. Many thanks.

Hi @kampta, do you know what is the meaning of remapping now?

Hi, The disparity maps contain some NAN values in the occlusion regions due to ZED cameras. Thus, it's correct when you read some NAN values in EXR files. In this...

Currently, we have only released the model for face restoration, the models for color enhancement and inpainting are not released yet.

Hi all, thanks for your big interest in this work. This paper is under review now, thus, we plan to release the training code and other models once the paper...

Hi @hzluyali, this is always a challenging issue in the face restoration task, which is hard to handle large degradation and preserve the identity content with a single model. You...