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 .
DETAILED ACTION
Summary
This office action for US Patent application 18/593742 is responsive to communications filed on March 1st, 2024. Currently, claims 1- 40are pending are presented for examination.
Claim Objections
Claim 14 is/are objected to because the term “a generative diffusion prior” is not clear. The applicant is suggested to explain what it means.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. § 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-3, 5-6, 8-11, 14-25, 27-33, 35-40 is/are rejected under 35 U.S.C §102 (a)(2) as being anticipated by Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22).
Regarding claim 1, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) meets the claim limitations, as follows:
A method, comprising:
at a device:
training a diffusion model to be able to improve a quality of any given input image [i.e. the diffusion model 300; Fig. 3], wherein the training includes:
adding random noise to an input image over a plurality of steps of a forward diffusion process, to form a noisy image [i.e. add noise to training image using a forward diffusion process in N stages; paragraph. 0117, Fig. 10]; and
learning to remove the noise from the noisy image over a plurality of steps of a reverse diffusion process [i.e. the reverse diffusion process can predict the noise that was added by the forward diffusion process, and the predicted noise can be removed from the image to obtain the predicted image; paragraph. 0118, Fig. 10], wherein one or more aspects of the diffusion model are varied over one or more of the steps of the reverse diffusion process to provide variational inferencing during the reverse diffusion process [i.e. parameters of the diffusion model are updated based on a comparison between the predicted image and an actual image at each stage; paragraph. 0056, 0090, 0119-0120; Fig. 10];
wherein the trained diffusion model is universally able to handle different types of image improvement tasks [i.e. the diffusion model can be used for various image generation task; paragraph. 0061, Fig. 1].
Regarding claim 2, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 1.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 1, wherein the different types of image improvement tasks include two or more of:
Inpainting [i.e. paragraph. 0061],
super-resolution [i.e. paragraph. 0061],
deblurring, or sharpening.
Regarding claim 3, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 1.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 1, wherein the different types of image improvement tasks include inpainting to complete a given input incomplete image [i.e. Fig. 6].
Regarding claim 5, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 1.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 1, wherein the different types of image improvement tasks include deblurring to remove blurring from a given input image [i.e. generate a clean image has higher quality and less blurry; paragraph. 0025, 0027, 0031].
Regarding claim 6, all the claim limitations which are set forth and rejected as per discussion for claim 1.
Regarding claim 8, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the distribution of data represents an output image [i.e. the output image; Fig. 6].
Regarding claim 9, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the at least one observation includes a masked image [i.e. the input is the masked image; Fig. 6].
Regarding claim 10, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 9.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 9, wherein the distribution of data represents a non-masked image [i.e. the non-masked image output; Fig. 6].
Regarding claim 11, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the at least one observation is a two-dimensional (2D) image [i.e. the input is a 2D image; Fig. 6].
Regarding claim 14, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the diffusion model is a generative diffusion prior [i.e. diffusion models are a class of generative neural networks; paragraph. 0023].
Regarding claim 15, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein each timestep of the reverse denoising diffusion process utilizes a corresponding denoiser that is weighted based on a denoising signal-to-noise ratio at the timestep [i.e. the training component 215 computes a weighted signal-to-noise ratio loss; paragraph. 0048, 0133].
Regarding claim 16, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 15.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 15, wherein denoiser weights progressively decrease through the reverse denoising diffusion process [i.e. a reverse diffusion process gradually removes the noise from the noisy image; paragraph. 0064, 0075, 0152].
Regarding claim 17, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein each timestep of the reverse denoising diffusion process utilizes a corresponding denoiser that applies score-matching regularization to a measurement matching loss [i.e. apply loss_eps and loss_x0 to compute a weighted signal to noise ratio loss; paragraph. 0048, 0129-0130, 0133].
Regarding claim 18, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 17.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 17, wherein the measurement matching loss is a reconstruction loss computed from the at least one observation [i.e. the weighted signal to noise ratio loss includes the reconstruction loss; paragraph. 0048].
Regarding claim 19, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 17.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 17, wherein a diffusion trajectory is used for regularization [i.e. diffusion models gradually add noise and denoise data; paragraph. 0056, 0063-0064, 0074].
Regarding claim 20, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, further comprising, at the device:
processing the distribution of data through a forward denoising diffusion process of the diffusion model to form at least one second observation [i.e. create the image 320 from the image 305 from the forward diffusion process; Fig. 3]; and
processing the at least one second observation through the reverse denoising diffusion process to approximate a second distribution of data for the at least one second observation [i.e. create the image 330 from the image 320 from the reverse diffusion process; Fig. 3].
Regarding claim 21, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the diffusion model is usable for different downstream tasks [i.e. Figs. 6-7].
Regarding claim 22, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the diffusion model is used for inpainting [i.e. Fig. 6].
Regarding claim 23, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the diffusion model is used for medical imaging [i.e. machine learning is used broadly in image editing or image generation; paragraph. 0001-0002].
Regarding claim 24, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 6.
Furthermore, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the claim limitations as follows:
The method of claim 6, wherein the diffusion model is used for image restoration [i.e. Fig. 7].
Regarding claims 25, 33, all the claim limitations which are set forth and rejected as per discussion for claim 6.
Regarding claims 27, 35 all the claim limitations which are set forth and rejected as per discussion for claim 8.
Regarding claims 28, 36 all the claim limitations which are set forth and rejected as per discussion for claim 15.
Regarding claims 29, 37 all the claim limitations which are set forth and rejected as per discussion for claim 16.
Regarding claims 30,38 all the claim limitations which are set forth and rejected as per discussion for claim 17.
Regarding claims 31,39 all the claim limitations which are set forth and rejected as per discussion for claim 18.
Regarding claims 32, 40 all the claim limitations which are set forth and rejected as per discussion for claim 19.
Claim Rejections - 35 USC § 103
5. 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) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter 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 said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
6. Claims 4, 13 is/are rejected under 35 U.S.C §103 unpatentable over Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Chen et al. (US 20240161327 A1).
Regarding claim 4, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 1.
In the same field of endeavor, Chen et al. (US 20240161327 A1) discloses the claim limitations as follows:
The method of claim 1, wherein the different types of image improvement tasks include super-resolution to increase a resolution of a given input image [i.e. increasing image resolution; paragraph. 0004].
It would have been obvious to one with ordinary skill in the art before the filing date of the invention to modify the teachings of Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Chen et al. (US 20240161327 A1) in order to create a method as the claimed invention.
Regarding claim 13, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Chen et al. (US 20240161327 A1) discloses the following claim limitations as set forth in claim 6.
In the same field of endeavor, Chen et al. (US 20240161327 A1) discloses the claim limitations as follows:
The method of claim 6, wherein the at least one observation is in a first resolution, and wherein the distribution of data is in a second resolution that is greater than the first resolution [i.e. generating high-resolution images using a diffusion model; paragraph. 0004, 0028, 0065, 0107].
Claims 7, 26, 34 is/are rejected under 35 U.S.C §103 unpatentable over Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Xie et al. (US 20240169622 A1).
Regarding claim 4, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 1.
In the same field of endeavor, Chen et al. (US 20240161327 A1) discloses the claim limitations as follows:
The method of claim 6, wherein the at least one observation is included in at least a portion of an image [i.e. mask image 710; paragraph. 0104, Fig. 7-8].
It would have been obvious to one with ordinary skill in the art before the filing date of the invention to modify the teachings of Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Xie et al. (US 20240169622 A1) in order to create a method as the claimed invention.
Regarding claims 26, 34, all the claim limitations which are set forth and rejected as per discussion for claim 7.
Claims 12 is/are rejected under 35 U.S.C §103 unpatentable over Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Green et al. (US 20240282130 A1).
Regarding claim 12, Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) discloses the following claim limitations as set forth in claim 11.
In the same field of endeavor, Green et al. (US 20240282130 A1) discloses the claim limitations as follows:
The method of claim 11, wherein the distribution of data represents a three-dimensional (3D) image [i.e. the output is a 3D rendering data; paragraph. 0043, 0047, Fig. 2C].
It would have been obvious to one with ordinary skill in the art before the filing date of the invention to modify the teachings of Zheng et al. (US 20240169500 A1 with its filing date on 2022/11/22) in view of Green et al. (US 20240282130 A1) in order to create a method as the claimed invention.
Conclusion
Any inquiry concerning this communication or earlier communications form the examiner should be directed to Nam Pham, whose can be contacted by phone at (571)270-7352. The examiner can normally be reached on Mon—Thurs.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, CZEKAJ DAVID, can be reached on (571)272-7327.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) AT 866-217-9197 (too free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/NAM D PHAM/ Primary Examiner, Art Unit 2487
Prosecution Insights