junheum / bmbc Goto Github PK

Hi,

I downloaded your pretrained model, and calculated PSNR on the test split of Vimeo-90K. I obtained a PSNR of only 30.544 compared to 35.01 in your paper.

Can you help me what could have gone wrong? What are the specific pre-processing steps you followed (normalization, crop size) during testing? Is the available model the one used to report the final results in the paper?

If possible, can you share the exact script you used to benchmark your results in the paper?

I would like to ask where can I find the pre-training model, because when I test the code, I prompt that there is no pre-training model

Can you give a link to the Adobe240-fps data mentioned in the article?

Hi, nice work!

Sorry to bother you, if it's convenient, would you consider uploading training codes and datasets later?

Thank you sincerely！

Nice work!
Follow the steps you provided to install the environment, but there are such problems:
Traceback (most recent call last):
File "run.py", line 4, in
import torchvision.transforms.functional as TF
File "D:\Anaconda3\envs\BMBC\lib\site-packages\torchvision_init_.py", line 1, in
from torchvision import models
File "D:\Anaconda3\envs\BMBC\lib\site-packages\torchvision\models_init_.py", line 11, in
from . import detection
File "D:\Anaconda3\envs\BMBC\lib\site-packages\torchvision\models\detection_init_.py", line 1, in
from .faster_rcnn import *
File "D:\Anaconda3\envs\BMBC\lib\site-packages\torchvision\models\detection\faster_rcnn.py", line 7, in
from torchvision.ops import misc as misc_nn_ops
File "D:\Anaconda3\envs\BMBC\lib\site-packages\torchvision\ops_init_.py", line 1, in
from .boxes import nms, box_iou
File "D:\Anaconda3\envs\BMBC\lib\site-packages\torchvision\ops\boxes.py", line 2, in
from torchvision import _C
ImportError: DLL load failed: The specified module was not found。

HI,

How do we run the BMBC model for multi frame interpolation? run.py always seems to output one frame irrespective of the time_step parameter.

Thank you for providing the code and models. I was trying to test out some 3fps footage which turns out to be noisy when converted to 12ps. Here are the Input and Output footage.

Input:
https://drive.google.com/file/d/1a7bJxVp9yGlh7Pe2nSO-NrxkrIF4WBPh/view?usp=sharing

Output:
https://drive.google.com/file/d/1A7jhqLodgqNDhgAnmWliIkR57uLJDevx/view?usp=sharing

I don't understand what's causing this.