H.265 is based on incremental gains over time. The paradigms have largely remained the same. What are the odds of deep learning providing huge performance gains? Here is the main metric:
- Perceptual quality remains the same at 2x improvement in bit-rate.
- Assume unlimited compute power at encoder.
- No need for speed.
Of course, I understand this is a really ill-posed problem because there are so many factors involved. But if it can be done, what would give the performance gain? Is it the following?
- Larger CTUs instead of the 64x64 one in H.265. Perhaps even go towards object-based coding.
- Better block matching algorithms that map longer dependencies.
- Perceptual loss for block matching instead of MAD or MSE.