Brush Releases V0.3

Michael Rubloff

Michael Rubloff

Tags

Brush V0.3

Brush, the free to use gaussian splatting reconstruction platform, just made its first formal release since the beginning of this year.

The 0.3 version arrives with several large scale improvements to the system. Namely, the incorporation of a hybrid MCMC approach brings a stronger algorithm, without tanking reconstruction times. There is also a cap on the number of splats that can be contained in one scene, but at the ten million mark, it does allow for a larger amount of flexibility. However, if you have a smaller scene or want a predictable memory footprint, you can set a maximum number of splats.

In practice, you still get the behavior people like, splats expand first where the scene needs detail, but the system also explores like MCMC to cover the tricky viewpoints that large captures expose.

Scale is the other big theme. Training now works on datasets that are larger than RAM, which means you can start immediately while the dataloader streams what it needs. That alone makes iteration feel different, especially for outdoor or multi room scans. Brush also tightens a few fundamentals so training behaves more robustly. Bounds are derived from the splat volume rather than camera frustums, which stabilizes optimization when coverage is uneven. There are speedups to the backward pass, optional LPIPS for perceptual quality, and an SSIM implementation that uses a separable convolution. If you keep an init.ply in your dataset, Brush will use it automatically, and COLMAP layouts are preferred for import to avoid edge cases.

Amazingly, Brush can work directly in a Chrome or Edge browser, although it should still be more powerful directly through the executables, which are now available for Mac, Windows, and Linux. The web build gains a proper fullscreen mode, more efficient file IO, directory picking, and touch controls, plus a warnings panel that helps you catch issues without digging through logs. Under the hood, the WebAssembly modules now play nicely with bundlers, and there is a demo wired into Next.js, which makes it far easier to drop Brush into a modern app or internal review tool.

The UI has also been reworked to reduce friction. A simple grid and arrow-key transforms make it easy to square up the ground plane and nudge a model into place. Press F to jump into fullscreen during reviews, adjust the field of view on the fly, play or pause splat sequences, pick a background color that suits your scene, and scale splats for quick presentation tweaks. There is also a settings panel when you load a new dataset.

SuperSplat‘s compressed ply format is now supported too, though this is different from the newly introduced SOGs 2.0. Little format gotchas are handled more gracefully, including color name parsing, double-precision floats, and consistent sequence ordering inside ZIPs. On the developer side, compile times are down, the CLI prints the live splat count, and there is a Docker example if you want a clean environment to share across a team.

Brush is an impressive platform, free to use across a wide range of local training setups, and remains one of the few ways to train locally without an NVIDIA GPU. The user base has continued to grow over the year, with steady PRs and active collaboration on Discord.

Brush continues to be completely free to use and is Apache 2.0 licensed.

Featured

Recents

Platforms

CHCNAV CoMeta Exports 3D Gaussian Splats to 3D Tiles

CHCNAV CoMeta generates 3D Gaussian splatting from the same aerial triangulation as its orthomosaic, DSM and mesh, and exports splats to PLY and 3D Tiles.

Michael Rubloff

Sep 14, 2026

Platforms

CHCNAV CoMeta Exports 3D Gaussian Splats to 3D Tiles

CHCNAV CoMeta generates 3D Gaussian splatting from the same aerial triangulation as its orthomosaic, DSM and mesh, and exports splats to PLY and 3D Tiles.

Michael Rubloff

Research

Gaussian Light Transport Fits Global Illumination as a Mixture of 13D Gaussians

aussian Light Transport fits global illumination as a mixture of 13D Gaussians, training 10 to 23 times faster than Neural Radiosity in a few megabytes.

Michael Rubloff

Sep 14, 2026

Research

Gaussian Light Transport Fits Global Illumination as a Mixture of 13D Gaussians

aussian Light Transport fits global illumination as a mixture of 13D Gaussians, training 10 to 23 times faster than Neural Radiosity in a few megabytes.

Michael Rubloff

Platforms

Spark v2.2.0 Adds Faster LoD Traversal, Rust Decoders

v2.2.0 adds an experimental faster LoD splat traversal algorithm, replaces JavaScript splat decoders with Rust ones, and reports up to 20% faster sorting.

Michael Rubloff

Sep 14, 2026

Platforms

Spark v2.2.0 Adds Faster LoD Traversal, Rust Decoders

v2.2.0 adds an experimental faster LoD splat traversal algorithm, replaces JavaScript splat decoders with Rust ones, and reports up to 20% faster sorting.

Michael Rubloff

Platforms

ANNX Studio v1.1.11 Adds 360 Photo Project Creation

ANNX Studio v1.1.11 rebuilds its 360 panorama modeling pipeline as 2.0 and adds project creation from 360 still images, previously limited to 360 video.

Michael Rubloff

Sep 11, 2026

Platforms

ANNX Studio v1.1.11 Adds 360 Photo Project Creation

ANNX Studio v1.1.11 rebuilds its 360 panorama modeling pipeline as 2.0 and adds project creation from 360 still images, previously limited to 360 video.

Michael Rubloff

Trending Articles
  1. TRENDING
    Loading...
  2. TRENDING
    Loading...
  3. TRENDING
    Loading...
Michael Rubloff

Written by Michael Rubloff

Michael is the Founder and Managing Editor of Radiancefields.com

More from Michael Rubloff

More from Michael Rubloff

Platforms

CHCNAV CoMeta Exports 3D Gaussian Splats to 3D Tiles

CHCNAV CoMeta generates 3D Gaussian splatting from the same aerial triangulation as its orthomosaic, DSM and mesh, and exports splats to PLY and 3D Tiles.

Michael Rubloff

Sep 14, 2026

CHCNAV

Platforms

CHCNAV CoMeta Exports 3D Gaussian Splats to 3D Tiles

Michael Rubloff

Sep 14, 2026

CHCNAV

Platforms

CHCNAV CoMeta Exports 3D Gaussian Splats to 3D Tiles

CHCNAV CoMeta generates 3D Gaussian splatting from the same aerial triangulation as its orthomosaic, DSM and mesh, and exports splats to PLY and 3D Tiles.

Michael Rubloff

Sep 14, 2026

CHCNAV

Research

Gaussian Light Transport Fits Global Illumination as a Mixture of 13D Gaussians

aussian Light Transport fits global illumination as a mixture of 13D Gaussians, training 10 to 23 times faster than Neural Radiosity in a few megabytes.

Michael Rubloff

Sep 14, 2026

Gaussian Light Transport

Research

Gaussian Light Transport Fits Global Illumination as a Mixture of 13D Gaussians

Michael Rubloff

Sep 14, 2026

Gaussian Light Transport

Research

Gaussian Light Transport Fits Global Illumination as a Mixture of 13D Gaussians

aussian Light Transport fits global illumination as a mixture of 13D Gaussians, training 10 to 23 times faster than Neural Radiosity in a few megabytes.

Michael Rubloff

Sep 14, 2026

Gaussian Light Transport

Platforms

Spark v2.2.0 Adds Faster LoD Traversal, Rust Decoders

v2.2.0 adds an experimental faster LoD splat traversal algorithm, replaces JavaScript splat decoders with Rust ones, and reports up to 20% faster sorting.

Michael Rubloff

Sep 14, 2026

Spark

Platforms

Spark v2.2.0 Adds Faster LoD Traversal, Rust Decoders

Michael Rubloff

Sep 14, 2026

Spark

Platforms

Spark v2.2.0 Adds Faster LoD Traversal, Rust Decoders

v2.2.0 adds an experimental faster LoD splat traversal algorithm, replaces JavaScript splat decoders with Rust ones, and reports up to 20% faster sorting.

Michael Rubloff

Sep 14, 2026

Spark