DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, and 8–10 are rejected under 35 U.S.C. §103 as being unpatentable over Kupyn (Kupyn et al, DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better, 2019) in view of Wang (Wang et al, ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks, 2020).
Regarding claim 1, with deficiencies of Kupyn noted in square brackets [ ], Kupyn teaches a method for image motion deblurring ( ["Abstract"]: Kupyn discloses an end-to-end learned method for motion deblurring. ), comprising:
obtaining a motion-blurred image to be deblurred;
([Sec. 3, "DeblurGAN-v2 Architecture"]: Kupyn discloses DeblurGAN-v2 to restore a sharp image
I
S
from a single blurred image
I
B
, via the trained generator. )
inputting the obtained blurred image into a pre-constructed and pre-trained image motion deblur model based on a multi-scale feature fusion module [ and a local channel information interaction module ] to obtain a clear image;
( ["Abstract"], [Sec. 1, "Introduction"] & [Sec. 3.1 , "Feature Pyramid Deblurring"]: Kupyn teaches inputting the blurred image into a trained generator that restores a sharp image, and further teaches introducing a Feature Pyramid Network (FPN) as a core building block in the generator. )
wherein, the image motion deblur model is obtained through extracting characteristic information of different spatial scales and frequencies through the multi-scale feature fusion module for feature fusion, [ and exchanging a fused feature map with local channel information in an one-dimensional convolution manner through the local channel information interaction module, ] and then training a dataset with a objective of minimizing a loss function based on adversarial loss and content loss.
( [Sec. 3.1 , "Feature Pyramid Deblurring"]: Kupyn teaches extracting and compressing / fusing characteristic information of different spatial scales through the multi-scale feature fusion module because Kupyn explains that FPN is introduced to incorporate multi-scale features, and that the architecture takes five final feature maps of different scales, upsamples them to the same input size, and concatenates them into one tensor containing semantic information on different levels; and in [Sec. 3.3 , "Double-Scale RaGAN-LS Discriminator"], Kupyn further teaches training the model using a hybrid loss including adversarial loss and content loss. )
Kupyn teaches multi-scale feature aggregation, it takes five feature maps of different scales, upsamples them, concatenates them into one tensor, and then applies upsampling / convolution layers plus a direct skip connection; however, as noted above in square brackets, kupyn fails to disclose expressly the local channel information interaction module using 1D convolution to assign channel weights where Wang teaches:
a pre-constructed and pre-trained image model based on a multi-scale feature fusion module and a local channel information interaction module
( [Sec. 3, "Proposed Method"] & [Sub-Sec. 3.2.2, "Local Cross-Channel Interaction"]: Wang teaches an efficient channel attention (ECA) module that learns channel attention from aggregated convolution features without dimensionality reduction and captures local cross-channel interaction; adaptive kernel to generate the features that are to be aggregated.)
and exchanging a fused feature map with local channel information in a one-dimensional convolution manner through the local channel information interaction module
( [Sec. 3, "Proposed Method"], [Sub-Sec. 3.2.2, "Local Cross-Channel Interaction"] & [Sub-Sec. 3.3, "ECA Module for Deep CNNs"]: Wang teaches that the weight of a channel is calculated by considering interaction between that channel and its
k
adjacent channels [Eq. 6], and further teaches that such strategy can be readily implemented by a fast 1D convolution with kernel size of
k
[Eq. 7], specifically
ω
=
σ
C
1
D
k
y
, where
C
1
D
indicates 1D convolution [Eq. 8]; Wang also teaches that, after aggregating convolution features, the ECA module performs 1D convolution followed by a sigmoid function to learn channel attention. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Kupyn’s multi-scale feature-fusion deblurring model to further include Wang’s local channel information interaction module, including 1D convolution-based channel weighting, because Kupyn already aggregates multi-scale convolutional features to restore a sharp image, and Wang teaches that local cross-channel interaction may be efficiently captured from aggregated convolution features by a lightweight ECA module using fast 1D convolution without dimensionality reduction. A person of ordinary skill in the art would have been motivated to apply Wang’s technique to Kupyn’s fused feature map in order to adaptively emphasize informative channels and suppress less useful or blur-degraded channels after multi-scale fusion, thereby predictably improving feature discrimination and image restoration quality while maintaining low computational cost, with a reasonable expectation of success
Regarding claims 8–10. The rationale provided for claim 1 is incorporated herein. In addition, the method for image motion deblurring claim 1 corresponds to the apparatus of claim 8, as well as the electronic device of claim 9, as well as the computer-readable storage medium of claim 10, and performs the steps disclosed herein. Further, Kupyn [as modified by Wang] further discloses that all programs run on a PC equipped with multiple GPUs. Therefore, the claims are all rejected.
Claims 2–4 are rejected under 35 U.S.C. §103 as being unpatentable over Kupyn [as modified by Wang] in view of Zhang (Zhang et al, EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network, 2021).
Regarding claim 2, Kupyn [as modified by Wang] teaches the method for image motion deblurring according to claim 1, wherein the constructed image motion deblur model comprises:
a convolutional layer for preliminary feature extraction, a plurality of residual blocks with the same structure, and a convolutional layer for image reconstruction;
( [Sec. 3.1, “Feature Pyramid Deblurring”]: Kupyn teaches the FPN module comprises “a bottom-up pathway” that is “the usual convolutional network for feature extraction” for the entire backbone network and further teaches that existing CNNs for image deblurring “typically refer to ResNet-like structures”; Kupyn also teaches that its architecture takes five final feature maps of different scales as output and “additionally add[s] two upsampling and convolutional layers at the end of the network to restore the original image size and reduce artifacts”. A convolutional layer for preliminary feature extraction is the entry point of the "Bottom-Up" pathway; In Kupyn's FPN, blocks provide the different "levels" (C2 through C5) that the pyramid uses is a plurality of residual blocks with the same structure. )
the residual block comprises the multi-scale feature fusion module
( [Sec. 3.1 , "Feature Pyramid Deblurring"]: Kupyn teaches that DeblurGAN-v2's FPN backbone outputs five final feature maps of different scales that are upsampled and concatenated into one tensor containing semantic information on different levels. )
and the local channel information interaction module;
( [Sub-Sec. 3.2.2, "Local Cross-Channel Interaction"]: Wang teaches an Efficient Channel Attention (ECA) module that is inserted into convolution / residual-style blocks and captures local cross-channel interaction. )
the multi-scale feature fusion module comprises [ a pyramid convolutional layer ] and a channel attention mechanism layer; and the local channel information interaction module comprises a global average pooling layer and an one-dimensional convolutional layer.
( [Fig. 2], [Sub-Sec. 3.2.2, “Local Cross-Channel Interaction”] & [Sub-Sec. 4.2.1, “MobileNetV2”]: Wang teaches a channel attention mechanism layer because ECA is an efficient channel-attention module; Wang further teaches that, after global average pooling, local cross-channel interaction is implemented by fast 1D convolution, specifically
ω
=
σ
C
1
D
k
y
, where
C
1
D
indicates 1D convolution. )
Kupyn [as modified by Wang] teaches using an Feature Pyramid Network (FPN) as a core building block in the generator and describes taking feature maps at different scales for multi-scale fusion, it uses a series of upsampling and convolutional layers at the very end to "collapse" the pyramid into a single output. However, it does not clearly call a pyramid convolutional layer in the sense where Zhang teaches:
the multi-scale feature fusion module comprises a pyramid convolutional layer
( [Sec. 1, “Introduction”] & [Sec. 3.2, “PSA Module”]: Zhang teaches a “multi-scale pyramid convolution structure” that processes the input at multiple scales, and further teaches that the SPC module performs multi-branch feature extraction using multi-scale convolutional kernels in a pyramid structure, and in [Fig. 4 & 5], shows parallel convolution branches with different kernel sizes and group sizes whose outputs are concatenated. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Kupyn [as modified by Wang] by configuring the multi-scale feature fusion module to include Zhang’s multi-scale pyramid convolution structure, because Kupyn [as modified by Wang] teaches multi-scale feature extraction and fusion in a deblurring generator, and a channel attention mechanism using global average pooling and 1D convolution for local cross-channel interaction, and Zhang teaches a pyramid-structured multi-branch convolution arrangement that processes input features at multiple scales and concatenates the resulting feature maps. Such modification would have predictably improved the network’s ability to capture and fuse blur-related features at different spatial extents and frequencies, while preserving Kupyn [as modified by Wang]’s efficient recalibration, thereby yielding no more than the predictable use of known deep-learning components for their established purposes.
Regarding claim 3, Kupyn [as modified by Wang and Zhang] teaches the method for image motion deblurring according to claim 2, wherein the step of extracting characteristic information of different spatial scales and frequencies through the multi-scale feature fusion module for feature fusion comprises:
obtaining an initial feature map
X
;
( [Page. 4, Sec. 3.2, “PSA Module”], & [Fig. 4]: Zhang teaches that the SPC module extracts the spatial information of the input feature map in a multi-branch way, where the input feature map is provided to parallel branches for subsequent multi-scale processing. )
conducting feature extraction on the obtained initial feature map
X
under different spatial scales and frequencies by using multiple types of convolutional kernels in the pyramid convolutional layer to obtain a plurality of sub-feature maps expressed as:
F
i
=
C
o
n
v
k
i
×
k
i
,
G
i
X
in the formula,
F
i
∈
R
C
'
×
H
×
W
represents the i-th sub-feature map obtained from the initial feature map
X
after passing through the
i
-th type of convolution kernel,
i
=
0,1
,
2
,
⋯
,
S
-
1
;
S
represents the type of convolution kernel;
R
represents the feature domain,
C
'
,
H
, and
W
respectively represent the number of channels, height, and width of the sub-feature maps,
C
o
n
v
represents the convolution operation;
k
i
×
k
i
represents the size of the i-th kernel;
G
i
represents the calculation parameter for the number of channels in the
i
-th type of convolutional kernel, expressed as follows:
G
i
=
2
k
i
-
1
2
,
k
i
>
3
1
,
k
i
=
3
;
( [Sec. 3.2, “PSA Module”, Eq. (3) & (4)] & [Fig. 4]: Zhang expressly teaches that the SPC module uses multi-scale convolutional kernels in a pyramid structure, with feature maps generated functions are defined. )
using the channel attention mechanism layer to obtain channel attention weights of each sub-feature map, and using the Softmax normalization function to calibrate the channel attention weights of each sub-feature map, the expression is:
Z
i
=
S
E
F
i
a
t
t
i
=
S
o
f
t
m
a
x
Z
i
=
exp
Z
i
∑
i
=
0
S
-
1
exp
Z
i
in the formula,
Z
i
∈
R
C
'
×
1
×
1
is the channel attention weight of the i-th sub-feature map,
S
E
represents the channel attention mechanism;
a
t
t
i
represents the normalized channel attention weight of the
i
-th sub feature map;
( [Sec. 3.2, “PSA Module”, Eq. (6-9)] & [Fig. 3 & 4]: Zhang teaches that the channel-wise attention vectors with different scales are obtained as
Z
i
=
S
E
W
e
i
g
h
t
F
i
, where
Z
i
∈
R
C
'
×
1
×
1
, and further teaches that a soft assignment weight is given by
a
t
t
i
=
S
o
f
t
m
a
x
Z
i
, thereby teaching the recited channel attention mechanism and Softmax normalization function to calibrate the channel attention weights of each sub-feature map. )
multiplying each sub-feature map with its corresponding normalized channel attention weight, and concatenating the multiplied feature maps using concatenation operation to obtain the fused feature map, expressed as:
Y
i
=
F
i
⊙
a
t
t
i
X
'
=
C
a
t
Y
0
,
Y
1
,
Y
2
,
⋯
,
Y
S
-
1
in the formula,
Y
i
represents the i-th sub-feature map with channel attention weights,
⊙
represents multiplication of channels;
X
'
represents the fused feature map, and
C
a
t
represents concatenation operation.
( [Sec. 3.2, “PSA Module”, Eq. (10-11)] & [Fig. 3]: Zhang teaches multiplying the re-calibrated weight
a
t
t
i
of the multi-scale channel attention with the feature map
F
i
of the corresponding scale to obtain
Y
i
, and further teaches that the refined output is obtained by concatenation as
O
u
t
=
C
a
t
Y
0
Y
1
⋯
Y
S
-
1
. )
Regarding claim 4, Kupyn [as modified by Wang and Zhang] teaches the method for image motion deblurring according to claim 3, wherein the step of exchanging the fused feature map with local channel information in the one-dimensional convolution manner comprises:
obtaining the fused feature map output by the multi-scale feature fusion module;
( [Sec. 3.2, “PSA Module”, Eq. (11)] & [Fig. 3]: Zhang teaches that, after the multi-scale feature maps are weighted, “the process to obtain the refined output can be written as
O
u
t
=
C
a
t
Y
0
Y
1
⋯
Y
S
-
1
”, corresponding to obtaining the fused feature map output by the multi-scale feature fusion module. )
using the global average pooling layer to perform a global average pooling operation on the fused feature map, the expression is:
y
=
g
X
'
=
1
W
H
∑
m
=
1
,
n
=
1
W
,
H
X
'
m
n
in the formula,
g
X
'
represents the global average pooling of the fused feature map,
W
,
H
respectively represents the width and the height of the fused feature map
X
'
,
X
'
m
n
represents the pixel values in the
m
-th row and the n-th column of the fused feature map
X
'
, and
y
represents the output;
( Wang, in [Sec. 3.2, “Efficient Channel Attention (ECA) Module”, Eq. (1) and surrounding text; Fig. 2 / introductory discussion]: Wang teaches that, for the output
X
of a convolution block,
y
=
g
X
, where
g
X
=
1
W
H
∑
i
=
1
,
j
=
1
W
,
H
X
i
j
, and further teaches that
g
X
is channel-wise global average pooling (GAP). )
the output
y
after global average pooled is interacted with the local channel information through the one-dimensional convolutional layer, expressed as:
ω
=
σ
C
o
n
v
1
D
k
y
in the formula,
ω
represents the channel attention weight after interaction,
C
o
n
v
1
D
k
represents the one-dimensional convolution kernel,
k
is the size of the convolution kernel, and
σ
represents the Sigmod activation function;
( [Sub-Sec. 3.2.2, “Local Cross-Channel Interaction”, Eq. (9)] & [Fig. 2]: Wang teaches that, after channel-wise global average pooling, ECA captures local cross-channel interaction and can be efficiently implemented by fast 1D convolution, specifically
ω
=
σ
C
1
D
k
y
, where C1D indicates 1D convolution. )
multiplying the channel attention weight
ω
with the fused feature map
X
'
to assign channel attention to the fused feature map
X
'
to obtain an information interaction feature map
X
'
'
.
( [Fig. 2] & [Sec. 3.2.2, “Local Cross-Channel Interaction”]: Wang teaches that, given the aggregated features obtained by global average pooling, ECA generates channel weights by fast 1D convolution and applies those weights to the feature map by element-wise product. )
Claim 5 is rejected under 35 U.S.C. §103 as being unpatentable over Kupyn [as modified by Wang and Zhang] in view of Wei (Wei et al, Dynamic scene deblurring and image de-raining based on generative adversarial networks and transfer learning for Internet of vehicle, 2021).
Regarding claim 5, Kupyn [as modified by Wang and Zhang] teaches the method for image motion deblurring according to claim 4, wherein the output of the residual block after processing the obtained initial feature map
X
is the result of adding the initial feature map
X
and the information interaction feature map
X
'
'
;
( Zhang, in [Sec. 1 “Introduction”], [Sec. 3.2 “PSA Module”] & [Fig. 5]: Zhang teaches that the proposed EPSA block is obtained by replacing the 3×3 convolution with the PSA module in the bottleneck blocks of the ResNet, and Fig. 5 shows the residual block with a “+” skip/add operation. The EPSA block can be easily added as a plug-and-play component into a well-established backbone network, and significant improvements on model performance can be achieved. )
Kupyn [as modified by Wang and Zhang] discloses residual-block add/skip idea in the EPSA/ResNet-style block for feature map X; however, it does not cleanly teach the requirement that the image-reconstruction portion comprises three convolutional layers where Wei teaches:
the convolutional layer for image reconstruction comprises three convolutional layers, and the output of the residual block after processed by the three convolutional layers is added to the obtained blurred image to obtain the final output clear image.
( Wei, [Abstract] & [Sec. 3, “Method”]: Wei teaches a residual block containing three 256-channel convolutional layers and further teaches a GAN-based motion-deblurring generator with a global skip connection block. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Kupyn, as modified by Wang and Zhang, in view of Wei to use a three-convolution image-reconstruction path whose output is added to the blurred input image, because Kupyn already teaches residual image restoration with an input-to-output skip connection, Zhang teaches residual-block addition for feature-map processing, and Wei teaches a three-convolution residual reconstruction path with a global skip connection in a motion-deblurring generator. Such modification would have predictably improved reconstruction of blur-related details while maintaining stable residual learning, and therefore would have amounted to no more than the predictable use of known CNN/GAN design techniques for their established purposes.
Claims 6–7 are rejected under 35 U.S.C. §103 as being unpatentable over Kupyn [as modified by Wang] in view of Kupyn'18 (Kupyn et al, DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks, 2018), further in view of Luo (Luo et al, Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices, 2020).
Regarding claim 6, Kupyn [as modified by Wang] teaches the method for image motion deblurring according to claim 1, wherein the training method of the image motion deblur model comprises:
Kupyn [as modified by Wang]'s DeblurGAN-v2 is based on a relativistic conditional GAN with a double-scale discriminator and introduces FPN into the generator; however, DeblurGAN-v2 fails to disclose the specific training recipe and the specific loss formulation where Kupyn'18's DeblurGAN teaches, with deficiency of Kupyn'18 in square brackets [ ]:
[ compressing the collected images in the dataset into images with a resolution of 360×360 and ] randomly cropping the image to the size of 256×256, then dividing them into a training set and a testing set;
( Kupyn’18, [Sec. 5, “Training Details”]: Kupyn’18 teaches that DeblurGAN was trained on random crops of size 256×256 from GoPro training dataset images. [Kupyn’18, Sec. 6.1, “GoPro Dataset”]: Kupyn ’18 further teaches that the GoPro dataset consists of 2103 pairs of blurred and sharp images and reports results on the GoPro test dataset of 1111 images. )
inputting the training set into the constructed image motion deblur model to reconstruct the deblurred image through multi-scale feature fusion and local channel information interaction;
( Kupyn [as modified by Wang] teaches the constructed image motion deblur model of claim 1, including multi-scale feature fusion and local channel information interaction. Wherein Kupyn’18, [Fig. 4], teaches that the generator network takes the blurred image as input and produces the estimate of the sharp image during training. )
conducting a supervised training on the model according to the testing set using a loss function based on adversarial loss and content loss;
( [Abstract]; [Sec. 1, “Introduction”]; [Sec. 3.2, “Network architecture”]; [Fig. 4]: Kupyn ’18 teaches supervised training of DeblurGAN using a multi-component loss function including Wasserstein GAN with gradient penalty (WGAN-GP) and perceptual / content loss, and teaches that the total loss consists of the WGAN loss from the critic and the perceptual loss. [Sec. 6.1, “GoPro Dataset”]: Kupyn’18 further teaches use of a separate GoPro test dataset for evaluation. Therfore, Kupyn’18 teaches supervised training using a loss function based on adversarial loss and content loss together with separate training and testing sets. )
repeating the training process to update the network parameters of the optimized model until the loss function converges or reaches the preset number of training iterations, and stop training to obtain the final optimized image motion deblur model.
( [Sec. 5, “Training Details”]: Kupyn’18 teaches iterative optimization of the generator and critic using Adam, with an initial learning rate of 10⁻⁴ for both generator and critic, and further teaches that after the first 150 epochs the learning rate is linearly decayed to zero over the next 150 epochs, thereby teaching repeating the training process to update network parameters through preset training iterations until training is completed to obtain the final optimized model. )
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to use the training recipe and loss formulation of Kupyn’18 to train the deblurring model of Kupyn [as modified by Wang], because Kupyn’18 teaches known crop-based supervised training, adversarial / content-loss optimization, separate training / testing use of the GoPro dataset, and iterative parameter updates for a closely related GAN-based motion-deblurring network, such that applying those known deblurring-training techniques to the modified Kupyn model would have been a routine implementation choice, as they are two versions of the same DeblurGAN’s system, yielding predictable results.
As noted above in square brackets [ ], Kupyn [as modified by Wang and Kupyn'18] still fails to disclose where Luo teaches:
compressing the collected images in the dataset into images with a resolution of 360×360 and randomly cropping the image to
( Luo, [Sec. VII "Technical Description, Sub-section B “Data preprocessing”]: Luo teaches a known image-preprocessing technique in which an image is cropped according to the shortest side to form a square intermediate image to 360x360, before resizing to the model’s required input size. Luo proves that 360×360 is just an intermediate square crop before resizing to the final network input.)
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to use Luo’s known 360×360 square-image preprocessing as an intermediate preparation step before the random 256×256 crop training of Kupyn’18, because Luo teaches standardizing image dimensions through square cropping prior to final input sizing, and Kupyn’18 teaches patch-based crop training for motion deblurring, such that combining these known preprocessing and training steps would have been a routine implementation choice with predictable results.
Regarding claim 7, Kupyn [as modified by Wang, Kupyn '18 and Lou] teaches the method for image motion deblurring according to claim 6, wherein the loss function based on the adversarial loss and the content loss is as follows:
L
t
o
t
a
l
=
L
a
d
v
+
λ
L
c
o
n
t
e
n
t
in the formula,
L
t
o
t
a
l
represents the loss function,
L
a
d
v
represents the adversarial loss,
L
c
o
n
t
e
n
t
represents the content loss,
λ
is a content loss coefficient; the adversarial loss
L
a
d
v
is expressed as WGAN-GP as below:
L
a
d
v
=
E
x
~
∼
P
g
D
x
~
-
E
x
∼
P
r
D
x
+
λ
E
x
^
∼
P
x
^
∇
x
^
D
x
^
2
-
1
2
in the formula,
D
represents discriminator,
x
represents clear image,
x
~
represents network output image,
x
^
represents random image,
x
^
=
ϵ
x
~
+
1
-
ϵ
x
,
ϵ
~
U
0,1
;
P
x
^
represents that a distribution of image samples uniformly sampled along a straight line between a pair of points
U
0,1
sampled from clear image distribution
P
r
and network output image distribution
P
g
;
( [Sec. 1, “Introduction”], [Sec. 2.2, “Generative adversarial networks”], [Sec. 3.1, “Loss function”], [Sec. 3.2, “Network architecture”], [Eq. (3-6)]: Kupyn’18 teaches that DeblurGAN is based on a conditional GAN and a multi-component loss function, and expressly teaches use of Wasserstein GAN with gradient penalty, further teaching that during training the critic network is WGAN-GP and that the total loss includes the WGAN loss from the critic. )
the content loss adopts perceptual loss, expressed as:
L
c
o
n
t
e
n
t
=
∑
ϕ
x
-
ϕ
(
x
~
)
2
2
in the formula,
ϕ
represents the pre-trained VGG19 network.
( [Sec. 3.1 “Loss function”]: Kupyn’18 teaches that, instead of raw-pixel L1 (MAE) / L2 (MSE) loss, DeblurGAN adopts perceptual loss, which is an L2 loss based on the difference of the generated and target image CNN feature maps, and further teaches that the perceptual loss is the difference between the VGG-19 conv3.3 feature maps of the sharp and restored images, where the VGG19 network is pretrained on ImageNet, thereby teaching the claimed content loss based on a pre-trained VGG19 network. )
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEN KUDO whose telephone number is (571)272-4498. The examiner can normally be reached M-F 8am - 5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vincent Rudolph can be reached at 571-272-8243. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
KEN KUDO
Examiner
Art Unit 2671
/KEN KUDO/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights