FAGx - EDM

spongemintΛογισμικό & κατασκευή λογ/κού

2 Δεκ 2013 (πριν από 3 χρόνια και 7 μήνες)

74 εμφανίσεις


Their goals:
prepare
for the next generation of
stereoscopic 3DTV applications


by improving capture and display technology,


by building new applications such as 3D media sharing and
gaming


and by studying the 3D viewing/using/playing experience
through lab experiments and in people’s natural
environment.


My
goal/task
:
stereo
view interpolation for single
lens stereo
camera


small
baseline


adjustment
of stereo base and convergence
parameters


M1
-
M24 (Q1
2011
-

Q4
2012)


3DTV 2.0


Project
3DTV

requirements:


Stereo, small baseline


HD (1920
x
1080) cinematic input (and output)


Real
-
time, means to me: at least 15 fps, preferably 25
-
30 fps


High
-
quality, or at least decent ‘preview’
quality



Project
Fine

requirements:


Multi
-
view, wide(r) baseline


Sports scenes (football) input:


Players look
-
alike


Uniform background (green pitch, …)


Speed
vs

quality?

Requirements

Algorithm Core


Truncated separable approximation to an isotropic
Laplacian

kernel.


Advantages:


Large support windows


Separable: efficient GPU implementation


fewer costly texture fetches needed


Boundary
-
guided, less foreground
-
fattening


Cost = min(UL, UR, BL, BR, L, U, R, B, F)


For project Fine












Movies…

Results


On
a NVidia GeForce 8800 GTX
(yes, I know, old hardware by now
)


800x600
, #50: 11 fps


1024x768, #50: 7 fps


1920x1080, #50: 3 fps


800x600, #100: 6 fps


1024x768, #100: 4 fps


1920x1080, #100: 2
fps


Implementation ‘shortcuts’ due to GPU architecture limitations


Texture units, render targets, RGBA textures, …


Speed
vs

quality: limited depth/disparity range.

Limitations (1)

Limitations (2)

Limitations (3)


Slow on memory accesses:


Lots of ‘random’ memory accesses


vs

rectified

stereo


Needs a (too) large convolution kernel


to prevent mismatches caused by homogeneous background


Written in OpenGL and Cg (graphics pipeline)


high texture memory access latency


no (or limited) random
framebuffer

writes



CUDA:


Low level control over memory access


Less architecture specific limitations


CUDA
vs

Cg: on average
30%
speedup on a GeForce 8800 GTX

Limitations (4)

Cg
vs

CUDA


Locally Adaptive Support
-
Weights


High computational intensity for multi
-
view input: computes a different
convolution kernel with adaptive weights for each (
V
i
,
V
j
) image pair.


Yoon et al., Locally Adaptive Support
-
Weight Approach for Visual Correspondence Search



Next (1)


‘Refocus’ stereo feed by adjusting:


stereo base (inter camera/pupil distance)


convergence distance (camera/pupil angle)


Immersive Teleconferencing with Natural 3D Stereoscopic Eye Contact Using GPU Computing
, 3D Stereo Media 2009


Biological
-
Aware Stereoscopic Rendering in Free Viewpoint Technology using GPU Computing
, 3DTV
-
CON 2010

Next (2)


Occlusion
handling


T
emporal
aggregation


(Approximate) depth information: e.g
.
time
of
flight, Kinect, …


SLI: multi
-
GPU
















Future




FAD?

(Food And Discussion)