1. 09 Jan, 2013 3 commits
  2. 08 Jan, 2013 5 commits
  3. 12 Dec, 2012 1 commit
  4. 06 Dec, 2012 3 commits
  5. 19 Nov, 2012 1 commit
  6. 12 Nov, 2012 1 commit
  7. 08 Nov, 2012 1 commit
  8. 07 Nov, 2012 10 commits
  9. 26 Sep, 2012 2 commits
  10. 11 Sep, 2012 1 commit
  11. 05 Sep, 2012 6 commits
  12. 27 Jul, 2012 1 commit
  13. 26 Jul, 2012 1 commit
  14. 18 Jul, 2012 1 commit
    • Fiona Glaser's avatar
      Revert r2204 · 3d03b619
      Fiona Glaser authored
      People don't seem to like this so I'm just going to get rid of it.
      3d03b619
  15. 17 Jul, 2012 3 commits
    • Fiona Glaser's avatar
      Faster predictor checking with subme<3 · 2ec69418
      Fiona Glaser authored
      Fix a typo that made an early-skip less effective.
      Avoid a relatively unpredictable branch.
      Slightly changed output due to the typo-fix.
      ~50 cycles faster on Core i7.
      2ec69418
    • Fiona Glaser's avatar
      Try 8x8 transform analysis even when sub8x8 partitions are present · d026397b
      Fiona Glaser authored
      Turn off the sub8x8 partitions, try it, and turn them back on if it didn't help.
      Small compression improvement with p4x4 on (~0.1-0.5%).
      Also update related comments.
      d026397b
    • Fiona Glaser's avatar
      Support changing resolutions between passes with macroblock-tree · dea5d7a5
      Fiona Glaser authored
      Implement a basic separable bilinear filter to rescale the quantizer offsets.
      Structure inspired by swscale, but floating-point instead of fixed-point.
      Not as optimized as it could be, but it's quite fast already.
      
      Example compression penalties on a 720p video game recording:
      First pass with 720p and second as 480p: ~-1.5% (vs. same res)
      First pass with 480p and second as 720p: ~-3% (vs. same res)
      dea5d7a5