RethinkVSRAlignment icon indicating copy to clipboard operation
RethinkVSRAlignment copied to clipboard

(NIPS 2022) Rethinking Alignment in Video Super-Resolution Transformers

Results 4 RethinkVSRAlignment issues
Sort by recently updated
recently updated
newest added

When I run the code [psrt_sliding_arch.py] , I face one bug > Traceback (most recent call last): > File "model.py", line 969, in > x = model(x) > File "/home/ma-user/anaconda3/envs/PyTorch-1.8/lib/python3.7/site-packages/torch/nn/modules/module.py",...

Hello, I want to know how to train the sliding model?

Thanks for your great work! I wonder to reproduce the result of PSRT-Sliding in the paper. Do you have a plan to release the option of PSRT-Sliding?

Why does the PSRT_upsample function only use the feature from the second forward propagation, as seen [here](https://github.com/XPixelGroup/RethinkVSRAlignment/blob/main/archs/psrt_recurrent_arch.py#L252), while BasicVSR++ uses features from four propagations, as seen [here](https://github.com/XPixelGroup/BasicSR/blob/master/basicsr/archs/basicvsrpp_arch.py#L256)? Was there an...