# US 2019/0318455 A1 · Adding greater realism to a computer-generated image by smoothing jagged edges within the image in an efficient manner

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

- Number: US 2019/0318455 A1
- Document ID: US20190318455A1
- Status: Published application
- Kind: A1
- Application number: 16/363,941
- Filed: 2019-03-25
- Published: 2019-10-17
- Earliest claimed: 2018-04-12
- Assignees: NVIDIA Corporation
- Applicants: NVIDIA Corporation
- Inventors: Holger Heinrich Gruen; Adam Christopher Marrs; Josef B. Spjut; Rahul Sathe; Morgan McGuire
- Web page: https://patentgrep.com/patent/US20190318455A1

## CPC

- G06T 5/70: Denoising; Smoothing
- G06T 15/005: {General purpose rendering architectures}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/50: Depth or shape recovery
- G06T 15/06: Ray-tracing
- G06T 15/503: {Blending, e.g. for anti-aliasing}
- G06T 2200/28: involving image processing hardware
- G06T 2207/20182: Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
- G06T 2207/20192: Edge enhancement; Edge preservation
- G06T 2207/30168: Image quality inspection
- G06T 2210/08: Bandwidth reduction
- G06T 2210/21: Collision detection, intersection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

During the rendering of an image, specific pixels in the image are identified where antialiasing would be helpful. Antialiasing is then performed on these identified pixels, where antialiasing is a technique used to add greater realism to a digital image by smoothing jagged edges. This reduces a cost of performing antialiasing by reducing a number of pixels within an image on which antialiasing is performed.

## Claims

### Claim 1

A method comprising:
identifying complex pixels within a scene to be rendered; and
performing antialiasing on each of the complex pixels within the scene, utilizing ray tracing.

### Claim 2 (depends on 1)

The method of claim 1, wherein the complex pixels each include visible pixels that are partially covered by one or more instances of geometry within the scene.

### Claim 3 (depends on 1)

The method of claim 1, wherein the complex pixels are identified utilizing conservative rasterization.

### Claim 4 (depends on 3)

The method of claim 3, wherein the conservative rasterization is implemented over a plurality of passes of one or more instances of geometry within the scene.

### Claim 5 (depends on 4)

The method of claim 4, wherein a first pass of the conservative rasterization includes a depth pre-pass.

### Claim 6 (depends on 5)

The method of claim 5, wherein the depth pre-pass creates a depth buffer that stores depths for nearest/closest fully covered pixels.

### Claim 7 (depends on 4)

The method of claim 4, wherein a second pass of the conservative rasterization includes a pixel identification pass.

### Claim 8 (depends on 7)

The method of claim 7, wherein the pixel identification pass identifies and marks the complex pixels, utilizing a pixel shader.

### Claim 9 (depends on 1)

The method of claim 1, wherein performing the antialiasing includes determining point-sampling visibility for a sub-pixel area within each of the complex pixels, utilizing GPU ray tracing.

### Claim 10 (depends on 1)

The method of claim 1, wherein performing the antialiasing includes, for each of the complex pixels, analytically solving a geometry surface and a coverage of the geometry surface over the complex pixel.

### Claim 11 (depends on 1)

The method of claim 1, wherein performing the antialiasing includes evaluating visibility analytically.

### Claim 12

A system comprising:
a processor that is configured to:
identify complex pixels within a scene to be rendered; and
perform antialiasing on each of the complex pixels within the scene, utilizing ray tracing.

### Claim 13 (depends on 12)

The system of claim 12, wherein the complex pixels each include visible pixels that are partially covered by one or more instances of geometry within the scene.

### Claim 14 (depends on 12)

The system of claim 12, wherein the complex pixels are identified utilizing conservative rasterization.

### Claim 15 (depends on 14)

The system of claim 14, wherein the conservative rasterization is implemented over a plurality of passes of one or more instances of geometry within the scene.

### Claim 16 (depends on 15)

The system of claim 15, wherein a first pass of the conservative rasterization includes a depth pre-pass.

### Claim 17 (depends on 16)

The system of claim 16, wherein the depth pre-pass creates a depth buffer that stores depths for nearest/closest fully covered pixels.

### Claim 18 (depends on 15)

The system of claim 15, wherein a second pass of the conservative rasterization includes a pixel identification pass.

### Claim 19 (depends on 18)

The system of claim 18, wherein the pixel identification pass identifies and marks the complex pixels, utilizing a pixel shader.

### Claim 20

A method comprising:
rendering a non-antialiasing G-buffer for a scene;
identifying visible pixels within the scene that are partially covered by one or more instances of geometry; and
tracing rays through the identified pixels to generate samples for the G-buffer.