# US 2026/0087768 A1 · Hyperspace downsampler

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087768 A1
- Document ID: US20260087768A1
- Status: Published application
- Kind: A1
- Application number: 18/895,197
- Filed: 2024-09-24
- Published: 2026-03-26
- Earliest claimed: 2024-09-24
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Shubham Deepak PATEL; Pawan Aasudaram BUDHWANI; Saikumar KONDAPARTHI
- Web page: https://patentgrep.com/patent/US20260087768A1

## CPC

- G06T 3/4046: using neural networks
- G06V 10/32: Normalisation of the pattern dimensions
- G06T 3/04: Context-preserving transformations, e.g. by using an importance map (panospheric to cylindrical image transformations G06T3/12)
- G06V 10/30: Noise filtering
- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06V 10/82: using neural networks
- G06T 2207/10024: Color image
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20182: Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
- G06T 2207/20212: Image combination
- G06T 2210/08: Bandwidth reduction
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems and techniques are described herein for adjusting resolutions of input images. For example, a computing device can process an image to generate a feature map associated with spatio-channel data of the image. The computing device can generate, using a first encoder, a first feature weight map and a second feature weight map based on the spatio-channel data of the feature map. The computing device can apply a noise filter to the first feature weight map to generate a first downsampled feature weight map. The computing device can perform a selective pooling downsample of the second feature weight map to generate a second downsampled feature weight map. The computing device can generate, based on the first downsampled feature weight map and the second downsampled feature weight map, a reduced resolution representation of the image.

## Claims

### Claim 1

An apparatus for image downsampling, the apparatus comprising:
one or more memories configured to store one or more images; and
one or more processors coupled to the one or more memories and configured to:
process an image of the one or more images to generate a feature map associated with spatio-channel data of the image;
generate, using a first encoder, a first feature weight map and a second feature weight map based on the spatio-channel data of the feature map;
apply a noise filter to the first feature weight map to generate a first downsampled feature weight map;
perform a selective pooling downsample of the second feature weight map to generate a second downsampled feature weight map; and
generate, based on the first downsampled feature weight map and the second downsampled feature weight map, a reduced resolution representation of the image.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
apply the noise filter to the first feature weight map using a plurality of dilated convolutions and a convolutional range-gaussian filter to reduce outlier noise in the first feature weight map.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
process the image to generate the feature map using a transformation to shift pixel arrangements of the image across channels as patches, wherein the feature map is based on the patches.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
assign, using a second encoder, scores to a first plurality of features of the first feature weight map and a second plurality of features of the second feature weight map; and
remove features from the first plurality of features and the second plurality of features based on the scores.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the first feature weight map and the second feature weight map are instances of a same feature weight map.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
perform the selective pooling downsample using an adaptive threshold on frequency components of the second feature weight map.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
provide the reduced resolution representation of the image to a machine learning model to perform one or more tasks associated with objects represented in the reduced resolution representation.

### Claim 8 (depends on 7)

The apparatus of claim 7, wherein the machine learning model is a deep neural network.

### Claim 9 (depends on 7)

The apparatus of claim 7, wherein the machine learning model is trained using on-device training.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
determine to downsample the image based on a power saving mode of the apparatus.

### Claim 11 (depends on 1)

The apparatus of claim 1, wherein the feature map is a hyperspace map.

### Claim 12 (depends on 1)

The apparatus of claim 1, wherein the one or more processors are configured to:
adapt parameters of the first encoder based on a target machine learning model.

### Claim 13 (depends on 1)

The apparatus of claim 1, wherein the apparatus is a sub-component of a system, and wherein the system comprises a camera system, a display system, or a video coding system.

### Claim 14 (depends on 1)

The apparatus of claim 1, further comprising one or more cameras configured to capture the one or more images.

### Claim 15

A method for image downsampling, the method comprising:
processing an image to generate a feature map associated with spatio-channel data of the image;
generating, using a first encoder, a first feature weight map and a second feature weight map based on the spatio-channel data of the feature map;
applying a noise filter to the first feature weight map to generate a first downsampled feature weight map;
performing a selective pooling downsample of the second feature weight map to generate a second downsampled feature weight map; and
generating, based on the first downsampled feature weight map and the second downsampled feature weight map, a reduced resolution representation of the image.

### Claim 16 (depends on 15)

The method of claim 15, further comprising:
applying the noise filter to the first feature weight map using a plurality of dilated convolutions and a convolutional range-gaussian filter to reduce outlier noise in the first feature weight map.

### Claim 17 (depends on 15)

The method of claim 15, further comprising:
processing the image to generate the feature map using a transformation to shift pixel arrangements of the image across channels as patches, wherein the feature map is based on the patches.

### Claim 18 (depends on 15)

The method of claim 15, further comprising:
assigning, using a second encoder, scores to a first plurality of features of the first feature weight map and a second plurality of features of the second feature weight map; and
removing features from the first plurality of features and the second plurality of features based on the scores.

### Claim 19 (depends on 15)

The method of claim 15, further comprising:
performing the selective pooling downsample using an adaptive threshold on frequency components of the second feature weight map.

### Claim 20 (depends on 15)

The method of claim 15, further comprising:
providing the reduced resolution representation of the image to a machine learning model to perform one or more tasks associated with objects represented in the reduced resolution representation.
