Get the newsletter
Google · AI / ML · Filed Sep 23, 2025 · USPTO published Sep 17, 2026 · Sep 17 release

Google Patents a Faster Tool for Building Lifelike Scenes Without Blurry Edges

When AI systems reconstruct a 3D scene from photos, the results can be riddled with jagged edges and missing details. Google has filed a patent for a faster, cleaner approach that attacks both problems at once.

A step-by-step process for generating a scene with improved detail and reduced blur. Drawing from patent filing US 2026/0278918 A1.
A step-by-step process for generating a scene with improved detail and reduced blur.All 11 drawings ↓
Publication number
US 2026/0278918 A1(US20260278918A1)
Applicant
Google LLC
Filed · Published
Sep 23, 2025 · Sep 17, 2026
Inventors
Jonathan Tilton Barron, Benjamin Joseph Mildenhall, Dor Verbin, Pratul Preeti Srinivasan, Lars Peter Johannes Hedman
Status when we published
Waiting for an examiner
Document
20 claims
US classification
345/427
Parent application
National Stage Entry of PCT/US2023/085765 (filed Dec 22, 2023)(PCTUS2023085765)

What Google's NeRF aliasing fix actually does for 3D images

Ever tried to zoom in on a photo only to find it turns into a blocky mess? AI-generated 3D scenes have the same problem, and fixing it usually means a much slower rendering process.

Google's patent describes a system for building 3D scenes from ordinary 2D photos, a technology called Neural Radiance Fields (or NeRF). The tricky part: existing fast versions of NeRF use a grid structure that doesn't understand distance or scale, so close-up or far-away views end up with jagged edges and missing chunks of the scene.

The new approach samples the scene in a cone shape (the way a camera lens actually sees the world) and uses a mathematical smoothing technique to fill the grid more accurately. The result, according to Google, is fewer errors and faster training time than previous methods, which is a combination that's proven difficult to pull off.

From the filing · CLAIM 1
… sampling a plurality of samples along a sampling direction of the multidimensional representation according to a multisampling pattern, the multisampling pattern representing a conical frustum …

Translation: The system shoots cone shaped rays into a digital 3d scene to gather color and depth data from multiple points at once.

How the cone-sampling and Gaussian method removes jagged edges

NeRF models work by learning, from a set of 2D photos, how a 3D scene looks from any angle. Faster NeRF variants speed things up by storing scene information in a feature grid, a 3D lookup table the model can query quickly. The problem is that grids have a fixed resolution, so when you ask for a view at a scale the grid wasn't built for, you get aliasing: jagged edges, flickering textures, or missing detail.

Google's system tackles this by changing how it samples the scene when building the grid. Instead of sampling along a thin ray (like a laser pointer), it samples along a conical frustum (the cone-shaped volume a camera pixel actually captures). This is a more realistic model of how a lens works at different zoom levels and distances.

From those cone samples, the system generates isotropic Gaussians (smooth, bell-curve-shaped blobs that represent uncertainty about exactly where a point is in space). Those blobs are then interpolated (blended) into the feature grid, effectively letting the grid understand scale and smooth over the gaps that cause artifacts.

The output goes into a proposal model, a lightweight neural network that focuses rendering effort on the parts of the scene that actually matter, and the final result is a clean 2D view of the scene from any angle.

From the filing · THE ABSTRACT
… these grid-based approaches lack an explicit understanding of scale and therefore often introduce aliasing, usually in the form of jaggies or missing scene content …

Translation: Traditional fast 3D rendering methods struggle to understand object sizes, which causes jagged lines and visual glitches.

What this means for AI-generated 3D photography and maps

NeRF technology is at the center of how companies like Google build photorealistic 3D maps, street-view reconstructions, and AR experiences from real-world photos. Right now, the fastest NeRF methods trade away image quality, while the highest-quality methods train too slowly for practical use. A system that closes both gaps at once matters across a wide range of products from mapping to content creation.

For you as an end user, the downstream effect could be sharper, more accurate 3D scenes in products like Google Maps or Google Photos, especially in tricky situations like aerial imagery at different zoom levels, where aliasing problems are most visible.

Google's 18th filing in the AI simulation space we've tracked since May adds to a run that includes one mapping 3D scenes from photos and one where AI rehearses future moves.

Source: US 2026/0278918 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Google patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 11 sheets

11 drawing sheets from US 2026/0278918 A1 · click any drawing to enlarge

Computing devices and training system., drawing sheet 1 from US 2026/0278918 A1
Sheet 1 Computing devices and training system.
Computing device applications and sensors., drawing sheet 2 from US 2026/0278918 A1
Sheet 2 Computing device applications and sensors.
Computing device with central intelligence., drawing sheet 3 from US 2026/0278918 A1
Sheet 3 Computing device with central intelligence.
View generation model input/output., drawing sheet 4 from US 2026/0278918 A1
Sheet 4 View generation model input/output.
Scene generation method comparison., drawing sheet 5 from US 2026/0278918 A1
Sheet 5 Scene generation method comparison.
Training and testing 3D models., drawing sheet 6 from US 2026/0278918 A1
Sheet 6 Training and testing 3D models.
Scene generation process., drawing sheet 7 from US 2026/0278918 A1
Sheet 7 Scene generation process.
Comparison of scene rendering approaches., drawing sheet 8 from US 2026/0278918 A1
Sheet 8 Comparison of scene rendering approaches.
Show the other 3 sheets
Google Patents a Faster Tool for Building Lifelike Scenes Without Blurry Edges patent drawing, sheet 9
Sheet 9
Google Patents a Faster Tool for Building Lifelike Scenes Without Blurry Edges patent drawing, sheet 10
Sheet 10
Google Patents a Faster Tool for Building Lifelike Scenes Without Blurry Edges patent drawing, sheet 11
Sheet 11
Patent filing page

Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.