Boosting neural video codecs by exploiting hierarchical redundancy

被引:3
|
作者
Pourreza, Reza [1 ]
Le, Hoang [1 ]
Said, Amir [1 ]
Sautiere, Guillaume [1 ]
Wiggers, Auke [1 ]
机构
[1] Qualcomm AI Res, San Diego, CA 92121 USA
关键词
D O I
10.1109/WACV56688.2023.00532
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In video compression, coding efficiency is improved by reusing pixels from previously decoded frames via motion and residual compensation. We define two levels of hierarchical redundancy in video frames: 1) first-order: redundancy in pixel space, i.e., similarities in pixel values across neighboring frames, which is effectively captured using motion and residual compensation, 2) second-order: redundancy in motion and residual maps due to smooth motion in natural videos. While most of the existing neural video coding literature addresses first-order redundancy, we tackle the problem of capturing second-order redundancy in neural video codecs via predictors. We introduce generic motion and residual predictors that learn to extrapolate from previously decoded data. These predictors are lightweight, and can be employed with most neural video codecs in order to improve their rate-distortion performance. Moreover, while RGB is the dominant colorspace in neural video coding literature, we introduce general modifications for neural video codecs to embrace the YUV420 colorspace and report YUV420 results. Our experiments show that using our predictors with a well-known neural video codec leads to 38% and 34% bitrate savings in RGB and YUV420 colorspaces measured on the UVG dataset.
引用
收藏
页码:5344 / 5353
页数:10
相关论文
共 50 条
  • [31] Neural Network Assisted Depth Map Packing for Compression Using Standard Hardware Video Codecs
    Siekkinen, Matti
    Kamarainen, Teemu
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 19 (05)
  • [32] Exploiting Perceptual Redundancy in Images
    Liu, Hongyi
    Chen, Zhenzhong
    VISUAL INFORMATION PROCESSING AND COMMUNICATION VI, 2015, 9410
  • [33] Exploiting modulation code redundancy
    Hogan, J
    OPTICAL DATA STORAGE '97, 1997, 3109 : 88 - 94
  • [34] Performance Analysis of Video Codecs Using Transport Stream Video
    Al Shayeji, Mohammad H.
    Ebrahim, Fahad
    Samrajesh, M. D.
    ADVANCED SCIENCE LETTERS, 2015, 21 (01) : 102 - 106
  • [35] On exploiting channel code redundancy
    Hogan, J
    ODS - 1997 OPTICAL DATA STORAGE TOPICAL MEETING, CONFERENCE DIGEST, 1997, : 38 - 39
  • [36] A Review of Emerging Video Codecs: Challenges and Opportunities
    Punchihewa, Amal
    Bailey, Donald
    2020 35TH INTERNATIONAL CONFERENCE ON IMAGE AND VISION COMPUTING NEW ZEALAND (IVCNZ), 2020,
  • [37] AS VIDEO CODECS MATURE, 2 TAKE THE SPOTLIGHT
    NASS, R
    ELECTRONIC DESIGN, 1995, 43 (24) : 65 - &
  • [38] A Comparative Performance Assessment of Different Video Codecs
    Valiandi, Ioanna
    Panayides, Andreas S.
    Kyriacou, Efthyvoulos
    Pattichis, Constantinos S.
    Pattichis, Marios S.
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, CAIP 2023, PT II, 2023, 14185 : 265 - 275
  • [39] Exploiting neural networks bit-level redundancy to mitigate the impact of faults at inference
    Catalan, Izan
    Flich, Jose
    Hernandez, Carles
    JOURNAL OF SUPERCOMPUTING, 2025, 81 (01):
  • [40] Making METOC data portable with video codecs
    Gommers, Daan
    Strik, Dennis
    van Leijen, Vincent
    2024 27TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION, FUSION 2024, 2024,