# US 2026/0087600 A1 · Per-asset denoising for real-time rendering of neural radiance fields (nerfs)

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

- Number: US 2026/0087600 A1
- Document ID: US20260087600A1
- Status: Published application
- Kind: A1
- Application number: 18/894,541
- Filed: 2024-09-24
- Published: 2026-03-26
- Earliest claimed: 2024-09-24
- Assignees: Adobe Inc.; The Regents of the University of California
- Applicants: Adobe Inc.; The Regents of the University of California
- Inventors: Sai Bi; Zexiang Xu; Xin Sun; Miloš Hašan; Kunal Gupta; Kevin Blackburn-Matzen; Kalyan Krishna Sunkavalli; Kai Zhang; Julien Olivier Victor Philip; Fujun Luan; Manmohan Chandraker; Iliyan Atanasov Georgiev
- Web page: https://patentgrep.com/patent/US20260087600A1

## CPC

- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/70: Denoising; Smoothing
- G06T 5/20: using local operators
- G06T 15/06: Ray-tracing
- G06T 15/08: Volume rendering
- G06T 15/506: {Illumination models}
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 19/20: Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

In implementing per-asset denoising for real-time rendering of neural radiance fields (NeRFs), a processing device receives a three-dimensional (3D) representation of a scene as a NeRF. The processing device generates an intermediate rendering of the scene using the NeRF. The intermediate rendering is denoised using a machine-learning model to generate a final rendering. The machine-learning model is trained on another rendering of this scene, which was rendered using a non-real-time, high-quality rendering scheme. In other words, the machine-learning model is optimized for each scene and provides a lightweight denoising network to provide real-time NeRF rendering while maintaining the high-quality visuals of non-real-time rendering schemes. The final rendering is then presented via a display device.

## Claims

### Claim 1

A method comprising:
receiving, by a processing device, a three-dimensional (3D) representation of a scene as a neural radiance field (NeRF);
generating, by the processing device and using the NeRF, a first rendering of the scene;
generating, using a machine-learning model, a second rendering of the scene by denoising the first rendering, the machine-learning model trained on a third rendering of the scene; and
presenting, by the processing device, the second rendering on a display device.

### Claim 2 (depends on 1)

The method of claim 1, wherein the machine-learning model is a convolutional neural network with ten or fewer convolutional layers.

### Claim 3 (depends on 2)

The method of claim 2, wherein the convolutional neural network includes three convolutional layers with three-by-three kernels and three-by-three rectified linear unit (ReLU) activations.

### Claim 4 (depends on 1)

The method of claim 1, wherein the presenting of the second rendering is performed in real-time.

### Claim 5 (depends on 1)

The method of claim 1, wherein the machine-learning model performs image-space denoising to remove noise directly from pixel values of the first rendering.

### Claim 6 (depends on 1)

The method of claim 1, wherein:
inputs to the machine-learning model include a red-green-blue (RGB) image of the first rendering and an alpha channel representation of the first rendering; and
outputs of the machine-learning model include a set of affinity features and bandwidth scalars to generate the second rendering from the first rendering.

### Claim 7 (depends on 6)

The method of claim 6, wherein the method further comprises:
computing, using the set of affinity features and bandwidth scalars, spatial kernels; and
applying the spatial kernels to the first rendering using a convolution operation to generate the second rendering.

### Claim 8 (depends on 7)

The method of claim 7, wherein an intensity of the spatial kernels is pooled based on an affinity of a local affinity feature value to a central-pixel affinity feature value.

### Claim 9 (depends on 1)

The method of claim 1, wherein training the machine-learning model on the 3D representation comprises:
generating one or more training set frames that include the third rendering as a ground truth image, an RGB image from a noisy rendering of the 3D representation, and an alpha channel of the noisy rendering; and
training the machine-learning model on the training set frames via standard gradient descent to minimize a reconstruction loss and a structure-preserving loss.

### Claim 10 (depends on 9)

The method of claim 9, wherein the third rendering is generated from the NeRF representation using a non-real-time rendering scheme.

### Claim 11

A system comprising:
a memory component; and
one or more processing devices coupled to the memory component, the one or more processing devices to perform operations comprising:
receive a three-dimensional (3D) representation of a scene as a neural radiance field (NeRF);
generate, using a Monte Carlo sampling algorithm, a first rendering of the scene in real-time;
generate, using a machine-learning model, a second rendering of the scene by denoising the first rendering, the machine-learning model trained on a non-real-time rendering of the scene; and
present the second rendering on a display device in real-time.

### Claim 12 (depends on 11)

The system of claim 11, wherein the machine-learning model is a convolutional neural network with ten or fewer convolutional layers.

### Claim 13 (depends on 12)

The system of claim 12, wherein the convolutional neural network includes three convolutional layers with three-by-three kernels and three-by-three rectified linear unit (ReLU) activations.

### Claim 14 (depends on 11)

The system of claim 11, wherein the machine-learning model performs image-space denoising to remove noise directly from pixel values of the first rendering.

### Claim 15 (depends on 11)

The system of claim 11, wherein:
inputs to the machine-learning model include a red-green-blue (RGB) image of the first rendering and an alpha channel representation of the first rendering; and
outputs of the machine-learning model include a set of affinity features and bandwidth scalars to generate the second rendering from the first rendering.

### Claim 16 (depends on 15)

The system of claim 15, wherein the one or more processing devices perform additional operations comprising:
compute, using the set of affinity features and bandwidth scalars, spatial kernels; and
apply the spatial kernels to the first rendering using a convolution operation to generate the second rendering.

### Claim 17 (depends on 16)

The system of claim 16, wherein an intensity of the spatial kernels is pooled based on an affinity of a local affinity feature value to a central-pixel affinity feature value.

### Claim 18 (depends on 11)

The system of claim 11, wherein the one or more processing device perform additional operations comprising train the machine-learning model on the 3D representation by:
generating one or more training set frames that include the non-real-time rendering as a ground truth image, an RGB image from a noisy rendering of the 3D representation, and an alpha channel of the noisy rendering; and
training the machine-learning model on the training set frames via standard gradient descent to minimize a reconstruction loss and a structure-preserving loss.

### Claim 19

A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:
receiving a three-dimensional (3D) representation of a scene as a neural radiance field (NeRF);
generating, using the NeRF, a first rendering of the scene;
generating, using a machine-learning model, a second rendering of the scene by denoising the first rendering, the machine-learning model trained on a non-real-time rendering of the scene; and
presenting the second rendering on a display device.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium of claim 19, wherein the machine-learning model is a convolutional neural network that includes three convolutional layers with three-by-three kernels and three-by-three rectified linear unit (ReLU) activations.
