Granted Patent B2

US 12,519,974 · App. 18/485,909 · Granted Jan 6, 2026

Inventors: Shubham Deepak Patel (Gondia, IN); Pawan Aasudaram Budhwani (Amravati, IN); Saikumar Kondaparthi (Hyderabad, IN)

Assignee: QUALCOMM Incorporated

H04N19/59G06T3/18G06T5/20G06T5/50G06V10/44G06V10/771H04N19/172G06T2207/20221

Abstract

Claims (89)

1 . An apparatus configured to process one or more frames, comprising:

one or more memories; and

one or more processors coupled to the one or more memories and configured to:

obtain a first frame from an image sensor;

downsample the first frame into a first downsampled frame based on a transfer function associated with the image sensor;

estimate the transfer function using a trained machine learning model;

downsample, using a downsampler of the trained machine learning model, a second frame captured by the image sensor to generate a second downsampled frame; and

estimate a super resolution kernel associated with the second downsampled frame; and

upsample the second downsampled frame based on the super resolution kernel to generate a second upsampled frame.

2 . The apparatus of claim 1 , wherein the one or more processors are configured to:

determine, using a discriminator of the trained machine learning model, a first feature map associated with the second downsampled frame;

compare the first feature map to a second feature map associated with the second frame; and

tune parameters of the downsampler based on a comparison of the first feature map to the second feature map.

3 . The apparatus of claim 2 , wherein the parameters comprise the estimated super resolution kernel.

4 . The apparatus of claim 1 , wherein the one or more processors are configured to:

identify a loss associated with the downsampling of the second frame based on the second frame and the second downsampled frame.

5 . The apparatus of claim 1 , wherein, to estimate the super resolution kernel, the one or more processors are configured to:

identify first features of the second frame based on applying a first convolutional filter to the second frame;

identify second features of the second downsampled frame based on applying a second convolutional filter to the second downsampled frame;

compare a first point spread function (PSF) associated with the first features and a second PSF associated with the second features; and

tune parameters of the second convolutional filter based on the comparison of the first PSF and the second PSF, wherein the parameters are associated with the super resolution kernel.

6 . The apparatus of claim 1 , wherein the one or more processors are configured to:

perform a first operation to upsample the second downsampled frame and generate a first portion of the second upsampled frame;

perform a second upsampling to upsample the second downsampled frame using the super resolution kernel into a second portion of the second upsampled frame; and

combine the first portion and the second portion into the second upsampled frame.

7 . The apparatus of claim 1 , wherein the one or more processors are configured to:

determine a type of the first frame based on a previous frame, wherein the previous frame is downsampled into a previous downsampled frame, wherein the type of the first frame comprises an independent frame or a dependent frame; and

modify the first downsampled frame based on the type of the first frame.

8 . The apparatus of claim 7 , wherein the one or more processors are configured to modify the first downsampled frame when the first frame corresponds to the dependent frame.

9 . The apparatus of claim 7 , wherein the one or more processors are configured to:

determine an optical flow between the previous frame and the first frame;

warp the previous downsampled frame based on the optical flow to generate a warped frame;

determine a residual error based on a comparison of the previous downsampled frame and the first downsampled frame; and

update the first downsampled frame based on the residual error.

10 . The apparatus of claim 1 , wherein a video encoder is configured to encode the second upsampled frame.

11 . The apparatus of claim 1 , wherein the transfer function comprises a point spread function.

12 . The apparatus of claim 1 , further comprising the image sensor, integrated into a camera, wherein the image sensor is configured to capture the first frame.

13 . An apparatus configured to process one or more frames, comprising:

one or more memories; and

one or more processors are coupled to the one or more memories and configured to:

receive a first frame;

determine a type of the first frame based on a previous frame, wherein the type of the first frame comprises an independent frame or a dependent frame;

upsample a first component of the first frame into a first portion based on a super resolution kernel based on the first frame corresponding to the independent frame;

upsample the first component and at least a second component of the first frame into a second portion; and

combine the first portion and the second portion into the first upsampled frame into the first upsampled frame.

14 . The apparatus of claim 13 , wherein the one or more processors are configured to:

form a hidden state component associated with a next frame from the second portion.

15 . The apparatus of claim 14 , wherein the hidden state component is applied to the next frame to generate a next upsampled frame.

16 . The apparatus of claim 13 , wherein the one or more processors are configured to:

determine a correlation between a hidden state component associated with the previous frame and a first component of the first frame;

generate an attention map based the hidden state component and features from the first component of the first frame;

blend the first component of the first frame based on the correlation and the attention map into an updated component; and

blend at least a second component of the previous frame with the updated component into the first upsampled frame.

17 . The apparatus of claim 13 , further comprising a display configured to display the first upsampled frame.

18 . An image signal processor configured to process one or more frames, comprising:

one or more processors coupled to one or more memories and configured to:

obtain a first frame from an image sensor;

downsample the first frame into a first downsampled frame based on a transfer function associated with the image sensor;

estimate the transfer function using a trained machine learning model;

downsample, using a downsampler of the trained machine learning model, a second frame captured by the image sensor to generate a second downsampled frame;

estimate a super resolution kernel associated with the second downsampled frame; and

upsample the second downsampled frame based on the super resolution kernel to generate a second upsampled frame.

19 . The image signal processor of claim 18 , wherein the one or more processors are configured to:

determine, use a discriminator of the trained machine learning model, a first feature map associated with the second downsampled frame;

compare the first feature map to a second feature map associated with the second frame; and

tune parameters of the downsampler based on a comparison of the first feature map to the second feature map.

20 . The image signal processor of claim 18 , wherein the parameters comprise an estimated super resolution kernel.

21 . The image signal processor of claim 18 , wherein the one or more processors are configured to:

identify a loss associated with the downsampling of the second frame based on the second frame and the second downsampled frame.

22 . The image signal processor of claim 18 , wherein the one or more processors are configured to:

estimate the super resolution kernel further comprises:

identify first features of the second frame based on applying a first convolutional filter to the second frame;

identify second features of the second downsampled frame based on applying a second convolutional filter to the second downsampled frame;

compare a first point spread function (PSF) associated with the first features and a second PSF associated with the second features; and

tune parameters of the second convolutional filter based on the comparison of the first PSF and the second PSF, wherein the parameters are associated with the super resolution kernel.

23 . The image signal processor of claim 18 , wherein the one or more processors are configured to:

perform a first operation to upsample the second downsampled frame and generate a first portion of the second upsampled frame;

perform a second upsampling to upsample the second downsampled frame using the super resolution kernel into a second portion of the second upsampled frame; and

combine the first portion and the second portion into the second upsampled frame.

24 . The image signal processor of claim 18 , wherein the one or more processors are configured to:

determine a type of the first frame based on a previous frame, wherein the previous frame is downsampled into a previous downsampled frame, wherein the type of the first frame comprises an independent frame or a dependent frame; and

modify the first downsampled frame based on the type of the first frame.

25 . The image signal processor of claim 24 , wherein the one or more processors are configured to:

modify the first downsampled frame when the first frame corresponds to the dependent frame.

26 . The image signal processor of claim 24 , wherein the one or more processors are configured to:

determine an optical flow between the previous frame and the first frame;

warp the previous downsampled frame based on the optical flow to generate a warped frame;

determine a residual error based on a comparison of the previous downsampled frame and the first downsampled frame; and

update the first downsampled frame based on the residual error.

Assignments (1)

Continuity (1)

References Cited (15)