The Camera Array Tool for Blender, developed by ToppiNappi (Olli Huttunen), generates camera rigs directly from 3D geometry. The add-on places virtual cameras at the centre of each polygon on a selected mesh and orients them according to the surface normal.

Users can decide whether the cameras face inward, outward, or in both directions. The tool allows the creation of custom rigs as well as prebuilt configurations, including grids, spheres, and cylinders. Once generated, the camera positions remain linked to the surface, meaning scaling or editing the underlying mesh automatically updates the rig.

Built for image-based reconstruction

Each camera in an array can render still images or animation sequences, stored in user-defined folders. The output data includes COLMAP text files—cameras.txt, images.txt, and points3D.txt—enabling direct use in 3D Gaussian Splatting (3DGS) or neural rendering workflows without the usual Structure-from-Motion reconstruction step. Point cloud exports can include colour data, accelerating later training phases in external applications. A density slider helps control file size when generating point clouds.

4DGS and animated datasets

Version 3.2.0 introduces 4DGS (Four-Dimensional Gaussian Splatting) data export for animated scenes. The add-on can render each frame from all cameras while generating corresponding COLMAP data per frame. This update fixes a previous COLMAP issue: files are now written immediately after each frame, preventing data loss if rendering is interrupted. A new “Animated Camera” feature enables rendering the same array setup through a single moving camera—an alternative method for producing dataset sequences.

Compatibility and workflow integration

Image series from the Camera Array Tool can be trained into Gaussian Splatting models using external software such as Postshot, NeRF Studio, Brush, or ToppiNappi’s free Postshot Batch Trainer. According to the developer, the add-on is particularly useful for synthetic dataset creation, virtual production, or academic experiments with neural rendering and multi-view reconstruction.

Simplicity over spectacle

Despite its experimental applications, the add-on’s concept remains simple: turn a mesh into a camera grid and render from every face. This direct approach makes it accessible for both research and practical visualisation tasks. The tool costs €36 and is available through Gumroad. The “Virtual Camera Bundle” combines the Camera Array Tool with the 360 Extractor add-on at a discounted rate.

As with all Blender extensions, users are advised to test the plug-in within their own pipeline before committing to production use.

The post Camera Arrays for the Gaussian Age first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

Khronos Group, in collaboration with OGC, Niantic Spatial, Cesium (Bentley), and Esri, has formally added 3D Gaussian Splats (3DGS) to the glTF ecosystem. Two experimental extensions, KHR_gaussian_splatting and KHR_gaussian_splatting_compression_spz, lay the foundation for interoperable splat workflows across DCCs, render engines, geospatial platforms, and the web.

This development places Gaussian Splats, until now a fast-moving research and tool-integration phenomenon, onto the same structural footing as meshes, point clouds, and textures. In other words: splats just got standardized.

From Research Trick to File Format

Gaussian splatting isn’t new. The math dates back to the 1990s, but the 2023 Inria paper “3D Gaussian Splatting for Real-Time Radiance Field Rendering” gave the technique a second life. By rendering 3D scenes as clouds of anisotropic Gaussian ellipsoids, each storing radiance and opacity, researchers achieved real-time neural rendering that rivaled neural radiance fields (NeRFs) without the training overhead.

What makes splats compelling is their efficiency: no polygons, no voxel grids, no heavy neural nets. Just point-based primitives that can capture detail in thin structures, soft translucency, or reflective materials.

Within a year, Houdini gained a native GSOPs plugin, V-Ray added splat rendering in Chaos Vantage, and studios began experimenting with splats in volumetric video pipelines such as HOLOSYS+. Now, the Khronos Group has moved to lock this fast-growing format into glTF, which already brands itself as the “JPEG of 3D.”

KHR_gaussian_splatting

The first of the new extensions, KHR_gaussian_splatting, defines how splats are represented inside glTF assets. Each splat is treated as a point primitive with the following attributes: Position (XYZ), Rotation (quaternion), Scale (anisotropic ellipsoid dimensions), Opacity and Spherical Harmonics coefficients for both diffuse and specular lighting

The extension allows fallback to sparse point clouds if a consuming renderer doesn’t support splats—ensuring that files remain viewable, even without specialized splat engines. For shader developers, the inclusion of spherical harmonics (SH) is key. SH enables compact representation of lighting across a hemisphere, which allows splats not only to look correct but also to respond naturally to lighting in real-time environments. Up to 3rd-degree SH coefficients are supported.

KHR_gaussian_splatting_compression_spz

The second extension, KHR_gaussian_splatting_compression_spz, tackles the elephant in the room: storage size. Traditional PLY splat datasets are enormous, with billions of points often required to reconstruct complex scenes. To address this, Niantic Spatial contributed the SPZ compression format, MIT-licensed for free use. SPZ achieves up to 90% smaller file sizes compared to equivalent PLY datasets while maintaining visual fidelity.

SPZ blobs can be embedded directly into glTF buffers. At runtime, they can either be streamed as compressed chunks or decompressed into raw primitives. This dual mode makes SPZ especially suited for geospatial and AR contexts where bandwidth is limited.

SPZ v2.0: Better Rotations

Version 2.0.0 of SPZ adds improved encoding of splat orientations. Rotations are stored as quaternions, but instead of four floats, SPZ encodes only the three smallest components as 10-bit signed integers. The missing largest component is reconstructed at runtime, with a 2-bit index flagging which component was omitted.

This compact scheme increases precision for long, thin geometry—think power lines, fences, antennas—and improves rendering stability in massive geospatial datasets. It’s the difference between “the wire looks straight” and “the wire jitters like a bad motion-capture solve.”

Why This Matters

1. Standardization
   Until now, Gaussian Splatting workflows were fragmented: PLY exports here, custom Houdini nodes there, and bespoke converters everywhere. With glTF extensions, splats can flow through established pipelines with predictable interoperability.
2. Production Viability
   Splats are great in research demos, but production requires stability. glTF’s adoption across web, AR, and DCC ecosystems ensures that Gaussian Splats won’t remain academic curiosities.
3. Performance & Compression
   SPZ addresses the practical bottleneck: dataset size. Geospatial datasets and volumetric captures can hit terabytes in raw splats; with SPZ, they become streamable assets.
4. Lighting Flexibility
   By embedding spherical harmonics, splats can sit naturally in lighting pipelines—whether inside Houdini’s Karma XPU, V-Ray, or CesiumJS streaming environments.

glTF as the “JPEG of 3D”

glTF’s trajectory has always been about unification and accessibility. From PBR textures to Draco compression, glTF brought complex 3D assets into a web- and engine-friendly format. Adding Gaussian Splats continues that trend, ensuring that cutting-edge formats don’t remain vendor-locked.

Roadmap and Next Steps

The current extensions are experimental—Khronos invites developers to test, validate, and propose refinements. Early validation across diverse geospatial datasets confirmed SPZ’s effectiveness, but the long-term plan is to extend the extensions with more attributes, compression modes, and streaming optimizations.

The post 3D Gaussian Splats Officially Added to glTF Standard first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

In the ever-evolving world of 3D graphics, staying ahead of the curve is crucial. Enter SuperSplat 2.0, the latest iteration of the open-source 3D Gaussian Splat editor by Will Eastcott. This update brings a suite of features designed to streamline workflows and enhance user experience.

https://twitter.com/i/status/1890036652057268591

HTML Viewer Export

Sharing your “splats” (3D point cloud representations) has never been easier. Previously, users had to host their own viewers—a task about as fun as debugging code on a Friday night. Now, with the new HTML viewer export feature, simply click ‘Publish,’ and your creation is live on the web with a shareable URL. No hosting hassles, just pure, unadulterated sharing bliss.

Timeline for Camera Animations

Creating smooth camera animations can often feel like herding cats. SuperSplat 2.0’s new Timeline feature aims to tame the chaos. To craft a seamless flythrough, select a frame, position the camera, set a keyframe, and repeat as needed. It’s animation made as straightforward as your morning coffee routine.

New Project File Format

As projects grow in complexity, so does the need for robust file management. SuperSplat now supports a new project file format with the .ssproj extension, allowing you to save your work between sessions. Think of it as a bookmark for your creative journey, ensuring you never lose your place.

Community Creations

With the enhanced publishing capabilities, you can now browse works from creators worldwide. Explore, learn, and draw inspiration from a global community, all within the SuperSplat ecosystem.

For more details and to dive into the splat-tastic world of SuperSplat 2.0, visit the official website at superspl.at. Stay updated by checking out the GitHub repository and following Will Eastcott on X/Twitter.

The post SuperSplat 2.0: Splatting Just Got Supercharged! first appeared on DIGITAL PRODUCTION and was written by Bela Beier.

The latest update to 3DGS Render, version 2.0, brings direct integration of 3D Gaussian splat editing into Blender. This enhancement aligns with the growing adoption of Gaussian splatting—a point-cloud-based rendering method praised for its potential in real-time graphics applications. By enabling direct editing of splats within Blender, 3DGS Render 2.0 could significantly simplify workflows in VFX, game development, and other post-production environments, provided its stability holds up under production testing.

Gaussian splatting (GS) renders 3D objects by mapping Gaussian distributions instead of relying on conventional polygonal geometry. This technique, lauded for its efficiency in real-time rendering, has gained traction due to its lightweight nature, especially in scenarios requiring rapid visualization. However, until now, GS editing was largely limited to proprietary tools, complicating adoption for artists reliant on established DCC (digital content creation) tools like Blender.

3DGS Render 2.0 bridges this gap with a Blender add-on, allowing users to import, manipulate, and render splat-based 3D assets directly. According to the developers, the plugin supports basic editing functions, making it easier for VFX artists to fine-tune splat-based assets without leaving their primary environment. Real-world applications of Gaussian splatting remain exploratory, but the update could streamline tasks like environment creation, particle effects, and lightweight asset previews, assuming the tools perform consistently in diverse production contexts.

The update is available for free, with the Blender plugin offered as an add-on for personal or professional use. More details and downloads can be found on the official 3DGS Render website.

Real-World Implications

For VFX pipelines and game design workflows, the Blender integration could simplify the process of experimenting with Gaussian splats, especially during previsualization or real-time rendering stages. However, as with any emerging technology, production artists are advised to test thoroughly before committing to GS for complex or critical assets.

While the potential of Gaussian splatting in speeding up rendering workflows is promising, stability and simplicity will determine whether this innovation transitions from niche experimental use to standard production pipelines. Users should evaluate whether the tool’s editing features are robust enough to support large-scale or multi-user projects.

Price: Free.

For a closer look at 3DGS Render 2.0 and its Blender integration, visit the official page.

The post 3dgs Render 2.0 Adds 3D Gaussian Splats Editing to Blender first appeared on DIGITAL PRODUCTION and was written by Bela Beier.