2012 IEEE International Conference on Multimedia and Expo 2012
DOI: 10.1109/icme.2012.7
|View full text |Cite
|
Sign up to set email alerts
|

A Unified 4/8/16/32-Point Integer IDCT Architecture for Multiple Video Coding Standards

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
52
0
1

Year Published

2013
2013
2022
2022

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 69 publications
(53 citation statements)
references
References 6 publications
0
52
0
1
Order By: Relevance
“…Park은 16x16 그리고 32x32 역변환 구조를 제시했다 [4] . Shen은 4/8/16/32-포인트 정수형 IDCT를 지원하는 곱셈 기 기반의 구조를 제안했다 [5] . 그리고 2013년에 Zhu는 파 이프라인 역변환 구조를 제안했다 [6] .…”
Section: 일정한 영상을 제공한다unclassified
“…Park은 16x16 그리고 32x32 역변환 구조를 제시했다 [4] . Shen은 4/8/16/32-포인트 정수형 IDCT를 지원하는 곱셈 기 기반의 구조를 제안했다 [5] . 그리고 2013년에 Zhu는 파 이프라인 역변환 구조를 제안했다 [6] .…”
Section: 일정한 영상을 제공한다unclassified
“…According to the input throughput of these architectures, the work frequency with 4096×2048@30 fps realtime application is as low as 4.19 MHz. Compared with [8], our architecture can save about 45% hardware overhead and only need 1/8 transpose memory peak bandwidth. Compared with [7], our architecture only need 25% input access bandwidth to deal with all kinds of block size and block mode of IDCT/IDST with higher hardware utilization rate while only increasing 15.7% hardware cost.…”
Section: 3mentioning
confidence: 99%
“…According to the paper, its hardware utilization rate maybe less than 80%. Since the reference [8]'s architecture is based on 32-point IDCT butterfly computation structure, most blocks of it will be idle during the variable block size IDCT process. According to previous statistical results, the percentage of 16×16 block size used for IDCT is 9.1%, 32×32 block size used for IDCT almost 1.3%.…”
Section: 3mentioning
confidence: 99%
See 1 more Smart Citation
“…Based on the traditional butterfly computational structure, S. Shen [3] et al presented a unified 4/8/16/32-point integer IDCT architecture in 2012 and W. Zhao [4] et al proposed a multiplierless inverse transform architecture in 2013, for HEVC 4K Â 2K video applications. To support different block size IDCT dynamically, P. T. Chiang [5] et al proposed a reconfigurable inverse transform architecture for HEVC 4K Â 2K video decoding in 2013.…”
Section: Introductionmentioning
confidence: 99%