# US 2026/0030834 A1 · Advanced rendering optimization techniques for 3d graphics

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

- Number: US 2026/0030834 A1
- Document ID: US20260030834A1
- Status: Published application
- Kind: A1
- Application number: 19/278,600
- Filed: 2025-07-23
- Published: 2026-01-29
- Earliest claimed: 2024-07-23
- Assignees: Unity Technologies SF
- Applicants: Unity Technologies SF
- Inventors: Alexander Suvorov; Ralph Leonard Hauwert
- Web page: https://patentgrep.com/patent/US20260030834A1

## CPC

- G06T 15/08: Volume rendering
- G06T 15/20: Perspective computation
- G06T 2210/62: Semi-transparency
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method of implementing directional opacity handling in Gaussian splats is disclosed. An approximate representation of a scene is received. 3D geometry data is generated. The 3D geometry data includes an approximate position and normal of each splat in a set of splats in the scene. Directional opacity values are calculated for the set of splats based on an application of a machine-learning model trained to optimize values of splat parameters, the values including the directional opacity values. The calculated directional opacity values are applied to the set of splats to enhance processing of the set of splats.

## Claims

### Claim 1

A non-transitory computer-readable storage medium storing a set of instructions that, when executed by one or more computer processors, causes the one or more computer processors to perform operations, the operations comprising:
receiving a representation of a scene;
generating a set of splats to represent the scene;
estimating splat parameters for each splat in the set of splats in the scene;
applying a machine-learning model trained to refine values of the estimated splat parameters, the values including directional opacity values; and
providing the refined values as an output usable to enhance subsequent processing of the set of splats.

### Claim 2 (depends on 1)

The non-transitory computer-readable storage medium of claim 1, the operations further comprising using the output to render each splat in the set of splats, the rendering including using the refined directional opacity values to render an opacity of the splat according to a view of the scene.

### Claim 3 (depends on 1)

The non-transitory computer-readable storage medium of claim 1, wherein the directional opacity values are represented using spherical harmonics to modulate an opacity of each splat based on a viewing angle of a viewer.

### Claim 4 (depends on 1)

The non-transitory computer-readable storage medium of claim 1, wherein the machine-learning model is trained by iteratively adjusting spherical harmonics coefficients to minimize a loss function that measures a difference between rendered outputs and actual scene appearances.

### Claim 5 (depends on 1)

The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise converting RGB color data to YUV color space for each splat, wherein the YUV color space separates luminance information from chrominance information.

### Claim 6 (depends on 1)

The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise segmenting the set of splats into groups based on similarity in material properties and applying shared parameters to each group.

### Claim 7 (depends on 1)

The non-transitory computer-readable storage medium of claim 1, wherein the operations further comprise performing post-processing operations including quantization of the splat parameters and filtering of the set of splats based on a visual contribution of each splat.

### Claim 8

A system comprising:
one or more computer processors;
one or more computer memories;
a set of instructions stored in the one or more computer memories, the set of instructions configuring the one or more computer processors to perform operations, the operations comprising:
receiving a representation of a scene;
generating a set of splats to represent the scene;
estimating splat parameters for each splat in the set of splats in the scene;
applying a machine-learning model trained to refine values of the estimated splat parameters, the values including directional opacity values; and
providing the refined values as an output usable to enhance subsequent processing of the set of splats.

### Claim 9 (depends on 8)

The system of claim 8, the operations further comprising using the output to render each splat in the set of splats, the rendering including using the refined directional opacity values to render an opacity of the splat according to a view of the scene.

### Claim 10 (depends on 8)

The system of claim 8, wherein the directional opacity values are represented using spherical harmonics to modulate an opacity of each splat based on a viewing angle of a viewer.

### Claim 11 (depends on 8)

The system of claim 8, wherein the machine-learning model is trained by iteratively adjusting spherical harmonics coefficients to minimize a loss function that measures a difference between rendered outputs and actual scene appearances.

### Claim 12 (depends on 8)

The system of claim 8, wherein the operations further comprise converting RGB color data to YUV color space for each splat, wherein the YUV color space separates luminance information from chrominance information.

### Claim 13 (depends on 8)

The system of claim 8, wherein the operations further comprise segmenting the set of splats into groups based on similarity in material properties and applying shared parameters to each group.

### Claim 14 (depends on 8)

The system of claim 8, wherein the operations further comprise performing post-processing operations including quantization of the splat parameters and filtering of the set of splats based on a visual contribution of each splat.

### Claim 15

A method comprising:
receiving an approximate representation of a scene;
receiving a representation of a scene;
generating a set of splats to represent the scene;
estimating splat parameters for each splat in the set of splats in the scene;
applying a machine-learning model trained to refine values of the estimated splat parameters, the values including directional opacity values; and
providing the refined values as an output usable to enhance subsequent processing of the set of splats.

### Claim 16 (depends on 15)

The method of claim 15, further comprising using the output to render each splat in the set of splats, the rendering including using the refined directional opacity values to render an opacity of the splat according to a view of the scene.

### Claim 17 (depends on 15)

The method of claim 15, wherein the directional opacity values are represented using spherical harmonics to modulate an opacity of each splat based on a viewing angle of a viewer.

### Claim 18 (depends on 15)

The method of claim 15, wherein the machine-learning model is trained by iteratively adjusting spherical harmonics coefficients to minimize a loss function that measures a difference between rendered outputs and actual scene appearances.

### Claim 19 (depends on 15)

The method of claim 15, further comprising converting RGB color data to YUV color space for each splat, wherein the YUV color space separates luminance information from chrominance information.

### Claim 20 (depends on 15)

The method of claim 15, further comprising segmenting the set of splats into groups based on similarity in material properties and applying shared parameters to each group.
