PMID- 37015524
OWN - NLM
STAT- Publisher
LR  - 20230404
IS  - 1941-0042 (Electronic)
IS  - 1057-7149 (Linking)
VI  - PP
DP  - 2022 Dec 7
TI  - Blind VQA on 360 degrees  Video via Progressively Learning from Pixels, Frames and Video.
LID - 10.1109/TIP.2022.3226417 [doi]
AB  - Blind visual quality assessment (BVQA) on 360 degrees  video plays a key role in 
      optimizing immersive multimedia systems. When assessing the quality of 360 degrees  
      video, human tends to perceive its quality degradation from the viewport-based 
      spatial distortion of each spherical frame to motion artifact across adjacent 
      frames, ending with the video-level quality score, i.e., a progressive quality 
      assessment paradigm. However, the existing BVQA approaches for 360 degrees  video neglect 
      this paradigm. In this paper, we take into account the progressive paradigm of 
      human perception towards spherical video quality, and thus propose a novel BVQA 
      approach (namely ProVQA) for 360 degrees  video via progressively learning from pixels, 
      frames and video. Corresponding to the progressive learning of pixels, frames and 
      video, three sub-nets are designed in our ProVQA approach, i.e., the spherical 
      perception aware quality prediction (SPAQ), motion perception aware quality 
      prediction (MPAQ) and multi-frame temporal non-local (MFTN) sub-nets. The SPAQ 
      sub-net first models the spatial quality degradation based on spherical 
      perception mechanism of human. Then, by exploiting motion cues across adjacent 
      frames, the MPAQ sub-net properly incorporates motion contextual information for 
      quality assessment on 360 degrees  video. Finally, the MFTN sub-net aggregates 
      multi-frame quality degradation to yield the final quality score, via exploring 
      long-term quality correlation from multiple frames. The experiments validate that 
      our approach significantly advances the state-of-the-art BVQA performance on 360 degrees  
      video over two datasets, the code of which has been public in 
      https://github.com/yanglixiaoshen/ProVQA.
FAU - Yang, Li
AU  - Yang L
FAU - Xu, Mai
AU  - Xu M
FAU - Li, Shengxi
AU  - Li S
FAU - Guo, Yichen
AU  - Guo Y
FAU - Wang, Zulin
AU  - Wang Z
LA  - eng
PT  - Journal Article
DEP - 20221207
PL  - United States
TA  - IEEE Trans Image Process
JT  - IEEE transactions on image processing : a publication of the IEEE Signal 
      Processing Society
JID - 9886191
SB  - IM
EDAT- 2023/04/05 06:00
MHDA- 2023/04/05 06:00
CRDT- 2023/04/04 20:06
PHST- 2023/04/04 20:06 [entrez]
PHST- 2023/04/05 06:00 [pubmed]
PHST- 2023/04/05 06:00 [medline]
AID - 10.1109/TIP.2022.3226417 [doi]
PST - aheadofprint
SO  - IEEE Trans Image Process. 2022 Dec 7;PP. doi: 10.1109/TIP.2022.3226417.