# US 2026/0278814 A1 · Reducing object tracking noise with pose smoothing

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

- Number: US 2026/0278814 A1
- Document ID: US20260278814A1
- Status: Published application
- Kind: A1
- Application number: 19/676,406
- Filed: 2026-05-13
- Published: 2026-09-17
- Earliest claimed: 2024-09-10
- Assignees: Snap Inc.
- Applicants: SNAP Inc.
- Inventors: Markus Diem; Blake Lucas; Thomas Muttenthaler; Daniel Wolf
- Web page: https://patentgrep.com/patent/US20260278814A1

## CPC

- G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments
- G06T 7/292: Multi-camera tracking
- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06T 5/20: using local operators
- G06T 5/70: Denoising; Smoothing
- G06T 7/55: from multiple images
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/30196: Human being; Person
- G06T 2207/30244: Camera pose
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Examples in the present disclosure relate to systems and methods for reducing noise in object tracking data. Images of an object are obtained via one or more cameras. The images are processed to obtain first pose data indicative of a pose of the object over time. The first pose data is represented in a camera space. The first pose data is transformed to second pose data represented in a world space. The second pose data is filtered using a smoothing filter to generate filtered pose data. The filtering includes, for each pose data item in a time series of the second pose data, using a rotation transformation between the world space and camera space to apply one or more camera space-specific filter parameters to the pose data item that is represented in the world space. The pose of the object is dynamically tracked based on the filtered pose data.

## Claims

### Claim 1

A method for facilitating object tracking, the method comprising:
processing a plurality of images of an object to obtain first pose data indicative of a pose of the object over time and represented in a camera space that is defined by a first coordinate system, the plurality of images captured using one or more cameras;
transforming the first pose data to second pose data represented in a world space that is defined by a second coordinate system;
filtering the second pose data using a smoothing filter to generate filtered pose data, the filtering of the second pose data comprising, for each respective pose data item in a time series of the second pose data, using a rotation transformation between the world space and the camera space to apply one or more camera space-specific filter parameters to the respective pose data item that is represented in the world space, the smoothing filter incorporating one or more scaling factors that adjust the filtering based on a distance between the object and the one or more cameras; and
dynamically tracking the pose of the object based on the filtered pose data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the one or more scaling factors comprise a scaling factor producing smoothing which increases as a function of the distance between the object and the one or more cameras to account for measurement uncertainty.

### Claim 3 (depends on 2)

The method of claim 2, further comprising:
computing the scaling factor using a position vector of the object represented in the camera space.

### Claim 4 (depends on 2)

The method of claim 2, wherein the scaling factor comprises a scaling matrix.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
tracking the distance between the object and the one or more cameras; and
dynamically updating the one or more scaling factors based on the distance.

### Claim 6 (depends on 1)

The method of claim 1, wherein the one or more camera space-specific filter parameters produce stronger filtering along a depth axis than along one or more other axes of the first coordinate system.

### Claim 7 (depends on 1)

The method of claim 1, wherein the method is performed by a computing device, the rotation transformation accounting for orientation of the first coordinate system relative to the second coordinate system, and the method further comprising:
tracking a pose of the computing device in the world space; and
dynamically updating the rotation transformation based on the pose of the computing device.

### Claim 8 (depends on 1)

The method of claim 1, wherein the method is performed by an extended reality (XR) device that comprises the one or more cameras, while the XR device is worn by a user.

### Claim 9 (depends on 8)

The method of claim 8, wherein the second coordinate system is defined in relation to a fixed point in a real-world environment in which the XR device is located while performing the object tracking, and the first coordinate system is movable relative to the second coordinate system as a result of movement of the XR device within the real-world environment.

### Claim 10 (depends on 1)

The method of claim 1, wherein the object comprises a hand.

### Claim 11 (depends on 1)

The method of claim 1, wherein the one or more cameras comprises a plurality of cameras, and wherein at least one of the rotation transformation or the one or more camera space-specific filter parameters is different for each respective camera of the plurality of cameras.

### Claim 12 (depends on 1)

The method of claim 1, wherein each respective pose data item in the time series comprises one or more positional coordinates represented in the world space.

### Claim 13 (depends on 1)

The method of claim 1, wherein the method is performed by an extended reality (XR) device, the method further comprising:
rendering virtual content for presentation to a user of the XR device;
determining positioning of the virtual content based at least partially on the pose of the object as tracked using the filtered pose data; and
causing presentation of the virtual content according to the determined positioning.

### Claim 14 (depends on 1)

The method of claim 1, wherein the smoothing filter comprises an adaptive filter.

### Claim 15 (depends on 14)

The method of claim 14, wherein the adaptive filter comprises, or is based on, a low-pass filter.

### Claim 16

An extended reality (XR) device comprising:
one or more cameras;
one or more processors; and
one memory storing instructions that, when executed by the one or more processors, cause the XR device to perform operations comprising:
capturing a plurality of images of an object using the one or more cameras;
processing the plurality of images to obtain first pose data indicative of a pose of the object over time and represented in a camera space that is defined by a first coordinate system;
transforming the first pose data to second pose data represented in a world space that is defined by a second coordinate system;
filtering the second pose data using a smoothing filter to generate filtered pose data, the filtering of the second pose data comprising, for each respective pose data item in a time series of the second pose data, using a rotation transformation between the world space and the camera space to apply one or more camera space-specific filter parameters to the respective pose data item that is represented in the world space, the smoothing filter incorporating one or more scaling factors that adjust the filtering based on a distance between the object and the one or more cameras; and
dynamically tracking the pose of the object based on the filtered pose data.

### Claim 17 (depends on 16)

The XR device of claim 16, wherein the one or more scaling factors comprise a scaling factor producing smoothing which increases as a function of the distance between the object and the one or more cameras to account for measurement uncertainty.

### Claim 18 (depends on 17)

The XR device of claim 17, the operations further comprising:
computing the scaling factor using a position vector of the object represented in the camera space.

### Claim 19 (depends on 16)

The XR device of claim 16, wherein the one or more camera space-specific filter parameters produce stronger filtering along a depth axis than along one or more other axes of the first coordinate system.

### Claim 20

One or more non-transitory computer-readable storage media, the one or more non-transitory computer-readable storage media including instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
processing a plurality of images of an object to obtain first pose data indicative of a pose of the object over time and represented in a camera space that is defined by a first coordinate system, the plurality of images captured using one or more cameras;
transforming the first pose data to second pose data represented in a world space that is defined by a second coordinate system;
filtering the second pose data using a smoothing filter to generate filtered pose data, the filtering of the second pose data comprising, for each respective pose data item in a time series of the second pose data, using a rotation transformation between the world space and the camera space to apply one or more camera space-specific filter parameters to the respective pose data item that is represented in the world space, the smoothing filter incorporating one or more scaling factors that adjust the filtering based on a distance between the object and the one or more cameras; and
dynamically tracking the pose of the object based on the filtered pose data.
