1

Highly Parallel Mode Decision Method for HEVC

Jun Zhang, Feng Dai, Yike Ma, and Yongdong Zhang

Picture Coding Symposium (PCS), 2013

2

OutlineIntroductionData dependency analysis and removingProposed methodImplementation and resultsConclusion

3

Introduction #1Coding Tree Unit

◦CU, TU, PU◦Depth

4

Introduction #2Motion vector prediction

◦Motion merge◦AMVP

5

Introduction #3Context adaptive binary arithmetic coding CABAC

6

Introduction #4Motion estimation region (MER)

◦Square◦Generally, the size of a MER is 32*32

MER MER

MER MER

7

Data dependency analysis and removing #1Data dependency between neighboring

PU◦After B0, B1, B2, A0, A1 are available, current

CU start to do motion vector prediction.

8

Data dependency analysis and removing #2Solution : Merge estimation region [12]

◦if a neighboring PU and the current PU belong to a same MER, this neighboring PU is treated as unavailable for spatial MVP derivation of the merge/skip MVP list construction process.

MER MER

MER MER

9

Data dependency analysis and removing #2

10

Data dependency analysis and removing #3HEVC uses only one entropy coding

method : CABAC

11

Data dependency analysis and removing #4If parallel MD in a MER containing multiple

CUs is expected, the encoder must solve the problem of CM absence for each CU because the encoding of neighboring CUs is also being performed and the accumulated CMs are not available yet.

12

Data dependency analysis and removing #5MD for all CUs in the same MER share a same

set of CMs that have been trained up to the last MER.

13

Data dependency analysis and removing #6Neighboring coding mode information is

needed to do CM selection or context modeling for a bin, which produces additional dependencies among CUs.

14

Data dependency analysis and removing #7

15

Proposed method #1The proposed parallel MD method is based on

MER and MD for all CUs in the same MER can be fully parallelized.

16

Proposed method #2Parallel processing among CUs

◦ MD for all potential CUs within the same MER, including CUs of same and different splitting depth are computed concurretnly, i.e. all nodes in the quadtree perform parallel MD.

17

Proposed method #3Parallel processing within a CU

◦ For a certain CU, many PU partition modes can be used and each one will give a RD cost with the corresponding coding information after ME and TU splitting computation. There are no explicit dependencies between these PU partition modes thus they can be conducted concurrently and independently.

18

Proposed method #4Parallel ME among Pus

◦ We propose that all PUs in a CU perform ME concurrently, including merge mode estimation and regular motion estimation. Because all CUs in the same MER are conducting MD concurrently, so actually ME for all PUs in the same MER are run in parallel.

19

Implementation and results #1

20

Implementation and results #2

21

Conclusion Small bitrate increasing and high encoding

speedup .Remove the dependency by MER.