A participant at a scientific conference engages deeply with a research poster from Purdue University, authored by Vishal Purohit, Junjie Luo, Yiheng Chi, and Qi Zhang. The poster, entitled "Generative Quanta," explores innovative methods in image colorization. The display includes complex diagrams, data charts, and sample images illustrating the efficacy of their approach to reconstructing color images from single input images. The research highlights addressing overexposure and underexposure issues through complex neural network algorithms. The dynamic environment showcases the active exchange of ideas, highlighted by the presence of various attendees exploring other posters in the background.
Text transcribed from the image:
9
P
Is it possible to recover
a color image from a
single one-bit image?
PURDUE
UNIVERSITY
Overexposed
Problem
Scence
F
Generative Quanta C
Vishal Purohit, Junjie Luo, Yiheng Chi, Qi
Poor
Colorization Results
Input Binary Image
Results
Continuously varying expos
Binary Camera
Colorization Neural
Network
(e.g. Pix2Pix)
Exposure
Correction
Module
e
th
Underexposed
39
a
Our method
Reconstructed
Color Image
ur Method
-Coefficient Decomposition
C
cxkxk
A'
Exposure Synthesis Method
mxkxk
cxcxm
Coefficients
Atoms
03
05
Pix2Pix-DNI
CycleGAN-DNI
SAVI21
DLOW
AtomODE-Pix2Pix (ours)
AtomODE-CycleGAN (ours)
Cat
MSE ()/RL (†)/FID (4)
3.75/0.9816/61.89
AFHQ (512 x 512)
Dog
MSE (4)/RL (†)/FID (↓)
5.91/0.9844/95.43
9.61/0.9816/207.82
41.15/46.27/178.29
2.44/0.9654/92.30
2.29/0.9997/57.88
1.15/0.9948/60.54
16.79/0.9824/220.90
46.27/0.9804/217.98
2.32/0.9489/173.65
3.17/0.9994/140.23
1.18/0.9971/87.43
W
MSE ()/RL
8.13/0.97
9.62/0.98.
38.87/0.90
2.75/0.962
2.15/0.99
1.23/0.99
Table 2. Colorization results on AFHQ and CelebA-HQ datasets. The input ima
index=0 of exposure burst. All the colorizers are trained using an image corr
we correct the overexposed input to correspond to the one used during training. I
of the exposure correction method used and colorizer is same across all the metho
Colorization Performance Comparison
DLOW
Input Non Adaptive Pix2Pix-DNI CycleGAN-DNI
SAVI21
Our Method
Ок