# US 2026/0065512 A1 · Fast bounding volume hierarchy tree rebuild for dynamic geometries using neural networks

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

- Number: US 2026/0065512 A1
- Document ID: US20260065512A1
- Status: Published application
- Kind: A1
- Application number: 18/821,034
- Filed: 2024-08-30
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: Advanced Micro Devices, Inc.
- Applicants: Advanced Micro Devices, Inc.
- Inventors: Binh Huy Le; Yang Shen; Madhusudhanan Srinivasan; Mark Richard Nutter; Aaron Michael Knoll
- Web page: https://patentgrep.com/patent/US20260065512A1

## CPC

- G06T 9/002: {using neural networks}
- G06T 9/001: {Model-based coding, e.g. wire frame}
- G06T 9/40: Tree coding, e.g. quadtree, octree
- G06T 13/20: Three-dimensional [3D] animation
- G06T 15/06: Ray-tracing
- G06T 2210/21: Collision detection, intersection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Techniques herein involve building bounding volume hierarchies for ray tracing using neural networks. These techniques use one trained neural network per animated mesh, with each such neural network being trained for a particular mesh topology. Meshes can be animated or otherwise modified to represent a single geometry object or portion of a geometry object in various animation states. Training a single neural network for each animated mesh allows such a neural network to generate BVHs for any animation state for the corresponding animated mesh in a robust manner. In other words, by limiting the responsibility of each such trained neural network to a single mesh topology (and therefore providing constraints to what the trained neural network must learn), it is possible for such a trained neural network to robustly and accurately generate BVHs.

## Claims

### Claim 1

A method comprising:
encoding a mesh to form a mesh encoding;
applying the mesh to a trained model to obtain a bounding volume hierarchy (“BVH”) encoding; and
expanding the BVH encoding to obtain a BVH for the mesh.

### Claim 2 (depends on 1)

The method of claim 1, wherein encoding the mesh comprises generating a sequence including, for a plurality of vertices of the mesh, positions of the vertices in order.

### Claim 3 (depends on 1)

The method of claim 1, wherein the mesh corresponds to an object of a scene and the trained model also corresponds to the object.

### Claim 4 (depends on 1)

The method of claim 1, wherein the BVH encoding includes a set of path encodings, wherein each path encoding describes a path from a root node to a leaf node of the BVH.

### Claim 5 (depends on 4)

The method of claim 4, wherein expanding the BVH encoding includes generating the BVH to have a set of non-leaf nodes defined by the set of path encodings.

### Claim 6 (depends on 5)

The method of claim 5, wherein the set of non-leaf nodes includes a union of non-leaf nodes implicitly indicated in the set of path encodings.

### Claim 7 (depends on 1)

The method of claim 1, further comprising applying a plurality of additional mesh encodings to a plurality of corresponding trained models to obtain a plurality of BVH encodings.

### Claim 8 (depends on 7)

The method of claim 7, wherein each additional mesh encoding corresponds to a different object of a scene.

### Claim 9 (depends on 1)

The method of claim 1, further comprising training the trained model by providing mesh training data comprising a plurality of training data items, wherein each training data item includes a mesh encoding and a corresponding BVH encoding, and wherein each training data item corresponds to a different animation state of a single object.

### Claim 10

A system comprising:
a memory configured to store a mesh; and
a processor configured to perform operations comprising:
encoding the mesh to form a mesh encoding;
applying the mesh to a trained model to obtain a bounding volume hierarchy (“BVH”) encoding; and
expanding the BVH encoding to obtain a BVH for the mesh.

### Claim 11 (depends on 10)

The system of claim 10, wherein encoding the mesh comprises generating a sequence including, for a plurality of vertices of the mesh, positions of the vertices in order.

### Claim 12 (depends on 10)

The system of claim 10, wherein the mesh corresponds to an object of a scene and the trained model also corresponds to the object.

### Claim 13 (depends on 10)

The system of claim 10, wherein the BVH encoding includes a set of path encodings, wherein each path encoding describes a path from a root node to a leaf node of the BVH.

### Claim 14 (depends on 13)

The system of claim 13, wherein expanding the BVH encoding includes generating the BVH to have a set of non-leaf nodes defined by the set of path encodings.

### Claim 15 (depends on 14)

The system of claim 14, wherein the set of non-leaf nodes includes a union of non-leaf nodes implicitly indicated in the set of path encodings.

### Claim 16 (depends on 10)

The system of claim 10, wherein the operations further comprise applying a plurality of additional mesh encodings to a plurality of corresponding trained models to obtain a plurality of BVH encodings.

### Claim 17 (depends on 16)

The system of claim 16, wherein each additional mesh encoding corresponds to a different object of a scene.

### Claim 18 (depends on 10)

The system of claim 10, wherein the operations further comprise training the trained model by providing mesh training data comprising a plurality of training data items, wherein each training data item includes a mesh encoding and a corresponding BVH encoding, and wherein each training data item corresponds to a different animation state of a single object.

### Claim 19

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
encoding a mesh to form a mesh encoding;
applying the mesh to a trained model to obtain a bounding volume hierarchy (“BVH”) encoding; and
expanding the BVH encoding to obtain a BVH for the mesh.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein encoding the mesh comprises generating a sequence including, for a plurality of vertices of the mesh, positions of the vertices in order.
