SLIDE 1
Outline
- Background
- System Description
- View Synthesis Collaboration Strategy
- View Synthesis Algorithm
- Evaluation
- Conclusion
Collaborative View Synthesis for Interactive Multi-view Video - - PowerPoint PPT Presentation
Collaborative View Synthesis for Interactive Multi-view Video - - PowerPoint PPT Presentation
Collaborative View Synthesis for Interactive Multi-view Video Streaming Fei Chen, Jiangchuan Liu, Yuan Zhao , Edith Cheuk-Han Ngai Outline Background System Description View Synthesis Collaboration Strategy View Synthesis
SLIDE 2
SLIDE 3
Background
SLIDE 4
Background
Character Multiview video enables users to enjoy the video from different
viewpoints.
Requirements for multiview streaming
- Rendering Quality: to reduce disparity of interview and smooth
the view sweeping process.
- Efficiency: to guarantee the availability of interactive
application
- Bandwidth Scalability: adaptive to available bandwidth of
users
SLIDE 5
System Description
Methods
- Multi view video coding
- Scalable video coding
- View Synthesis
Collaboration Strategy
Multiview Streaming Structure
SLIDE 6
View Synthesis Collaboration
Different strategies to generate visual views
Middle ¡synthesis Shi- ¡synthesis
SLIDE 7
View Synthesis Algorithm
- DIBR: Depth image based rendering
(a)Le- ¡Reference ¡View ¡(b)Right ¡Reference ¡View ¡(c)Synthesized ¡View ¡ (d)Original ¡View
SLIDE 8
View Synthesis Algorithm
- S-DIBR: Shift depth image based rendering
SLIDE 9
S-DIBR
- The shift value from the main reference view
to the visual view is:
2 ... , 2 , 1 , N n where N fdn S = = λ 2 ... , 2 , 1 ), 1 (
1
N n where N n fd S = − = λ ⎪ ⎩ ⎪ ⎨ ⎧ = ⊂ = ⊂
+ + M i i A i i
P P P P P P P P , ,
1 1
- The ¡shi- ¡value ¡from ¡the ¡visual ¡view ¡to ¡the ¡assistant ¡
reference ¡view ¡is: ¡
- Therefore ¡we ¡have ¡following ¡relaConship: ¡
SLIDE 10
View Synthesis Analysis
Different ¡view ¡comparison
SLIDE 11
View Synthesis Analysis
Synthesized ¡with ¡different ¡reference ¡views
SLIDE 12
Rendering Quality
- Similar rendering quality for 1 visual view
- S-DIBR keeps the performance stable as the
number of visual views increases
Rendering ¡quality ¡comparison ¡between ¡W-‑DIBR(warping ¡DIBR) ¡and ¡ S-‑DIBR(shi- ¡DIBR)
SLIDE 13
Efficiency
- The computation latency:
N T S T D T
N j j i A i j i M i
∑ ∏ ∏
= = =
+ − = − =
2 / 1 1 1
) ( 1 ) ( ) ( α α ϕ
] [ 2 )] )...( ( ) [( 2 ) (
2 / 1 1 2 / 1 1 2 / 2 / 2 2 1 1 1 ,
∑∏ ∑∏ ∑
= = = = =
+ = + + + + = =
N j j i A i N j j i M i A N M N A M A M N j p j p
KP P P P P P P K T S T α α
- The ¡Cme ¡cost ¡in ¡pixel ¡projecCon ¡for ¡S-‑DIBR:
- And ¡we ¡have ¡the ¡computaCon ¡latency ¡reducCon:
δ + = + + + =
p h t m p
NT T T T T N T ) (
SLIDE 14
Efficiency
- The computation latency reduction aggregates
as the number of visual views increases
computaCon ¡latency ¡comparison
SLIDE 15
Bandwidth Scalability
scalable ¡rendering ¡with ¡different ¡bitrates
SLIDE 16
Conclusion
- A collaborative view synthesis strategy
for multiview streaming system
- S-DIBR algorithm with rendering
quality, efficiency and bandwidth scalability
SLIDE 17