A detailed technical poster titled "Motion Deblurring with Unknown Modal Spatiotemporal Alignment" is displayed, featuring an array of complex diagrams, mathematical formulations, and visual data comparisons. The poster seems to be presented at an academic or professional conference, indicated by the CVPR (Conference on Computer Vision and Pattern Recognition) logo and the event details, "Seattle, WA, June 17-21, 2024," located in the upper right. The primary authors, affiliations, and contact information are listed in the top section: Jiyuan Zhang, Shiyan Chen, Yajing Zheng, Zhaofei Yu, and Tiejun Huang, associated with Peking University and the National Key Laboratory for Multimedia Information Processing and the Institute for Artificial Intelligence, Peking University.

The poster presents the methodology and results of a novel approach using a spike camera for motion deblurring. It outlines different stages, including Basic Image Deblurring, Flow-guided Dense Fusion, and attention-based dense fusion methods. The detailed graphics and charts illustrate different stages of implementation and the resulting deblurred images, with clear demarcation and performance metrics comparing methods like NAHEST, EFNet, REFID, and the proposed UASDNet.

An overview of the spike camera technology and principles is provided alongside the breakdown of light intensity and voltage correlation for capturing continuous photons. Comparative images showcasing the effectiveness of the deblurring techniques are displayed at the bottom, with quantitative performance scores. The contact email and a QR code linking to more detailed information about the research or the presenter’s profile are also included.

The educational and comprehensive layout captures the intricate details and depth of the research, aimed at an audience familiar with advanced computational imaging and deblurring techniques.
Text transcribed from the image:
otion Deblurring with Unknown Modal Spatiotemporal Alignment
n Zhang1,2, Shiyan Chen 12, Yajing Zheng1,2,+, Zhaofei Yu1,2,3,4, and Tiejun Huang1,2,3
e, Peking University 2 National Key Laboratory for Multimedia Information Processing, Peking University
3 Institute for Artificial Intelligence, Peking University
Stage 2: Bi-Deformable Aligning Enhancement
ge 1: Basic Image Deblurring
Image-based
B₁
Deblur Net
L₁
Stage-2 Net
Stage 3: Flow-guided Dense Fusion
pike[V
L₂
Stage-3 Net
L3
Spike Camera
RGB frame
S
{īs.}
Random
Sample
Coasre Intensity
Estimation
K
Ms21
{LS.}
BIDMA
H
{L}
Light
Intensity
ADB
ADB
L2
Flow Net
ADB
ADB
V
Voltage
TCVPR
SEATTLE, WA JUNE 17-21, 2024
Jiyuan Zhang
jyzhang@stu.pku.edu.cn
Principles of Spike Camera
Continuous Photons
I(t)
{S}
K
Spike Segments
Spikes
e a three-stage model named
Spike-guided Deblur Net (UaSDN)
L₁ FM (BOM),
L1, {Silk E [1,2,..., K]}: 0M₂),
L2. {Sk [1,2,..., K]}: 0M3).
Deformable Aligning Enhancement
APs
ΔΡΑ
BIDMA
BIDMA
Stage-2 Net
BIDMA: Bi-Directional Deformable Modal Align
Stage 3: Flow-guided Dense Fusion
Channel Attention Residual Dense Block
ADB
ADB
Transform
ADB
Stage-3 Net
ADB: Attention-based Dense Block
K coarse light intensity estimation
LS = FMs21 (S: 0MS21),
Concatenate {k E [1,2,..., K]}
and 2, and get the tiled image [tile
The U-shape network contains the
encoder and decoder. After
VSk−Ĺa = Ƒflow (ĽSK, Ĺ2), LS = G(LS VS →Ĺ₂), processing in the Attenion-based
+
{Ĺk € [1,2,..., K]}
24.02dB
25.76dB
23.15dB
Dense Block, the final predicted
deblurred images are output.
27.35dB
24.97dB
29.04dB
010101010010001001010101010
Readout
Sx,y(c)
0,
Vy(t)=
if ((c-1)T, CT], Vx,y(t) = 0,
otherwise,
Vry(t) + Ix,y(t), if V(t) < 0,
otherwise,
Where Vxy(t) and Vxty (t) denotes the voltage before an
receiving the electric current Ix,y (t), c E R. The spike st
output with the size of H x W x C after C times readout
Tμs (C =).
28.38dB
31.65dB
900-8330-1H
DC
FAL
49098
9098
9098
9091
AP $21
F+1
26.98dB
25.80dB
26.84dB
28.00dB
26.60dB
30.40dB
33.61dB
36.18dB
FA(F, F, AP),
Fe(FDCN (F, APs), Up(F+1)),
Fe(FL, Fs),
FA([FS, FL, APS),
Fe(FDCN (FS, APS21), Up(F+1)),
Fe(Fs, Ft),
32.68dB
31.84dB
31.96dB
32.83dB
31.44dB
33.50dB
30.03dB
33.28dB
Blur Image
HINet
NAFNet
EFNet
REFID
SpkDeblurNet
UaSDN(Ours)
Ground Truth
SpkDeblurNet
UaSDN (Ours)
G