Alex Izvorski
Alex Izvorski
Serhan, The code in h264_slice_data.c needs work before it would be usable. The following missing functions need to be implemented: - [ ] bs_read_ce - for CAVLC - [ ]...
@zhuwanling Could you please provide a couple of test examples of NIQE from Matlab? (images and scores) I know the NIQE code does not produce the expected results, but don't...
@fenollp Thank you! Yes these are all training times (forward + backward + weights update). Some other benchmarks only quote the forward+backward pass. I will change the description to make...
@marccospraiano Could you please provide the error message, and some info about your environment? (python version, versions of dependencies, operating system)
@DonaldTsang This is possible, however - from my experience with open source - I would like to see someone *actually do a better job* before taking the lead. Contribute some...
@slhck VQEG would be a nice home for this; it certainly is very close in terms of topic.
@choosehappy It's been a while so I don't remember exactly. I think it was producing outputs that did not match those in the original NIQE paper, although they did correlate...
@sunbinbin1991 Could you post a code+images example? I think slight degrees of blur only correspond to slight changes in NIQE. You need to blur a *lot* to see a big...
@peastman Thanks! This is great, also very excited you're working on it > Alternatively, should there be two separate offset vectors, one that's a simple offset and one that scales...
@peastman Hmm, that's true for arbitrary R, but this seems to be how cif files think about it. I think they have a mix of reflections and translations, neither of...