Cross-platform baseline for storing 3D Gaussian splats in glTF while enabling future innovation; Community feedback invited before ratification
Beaverton, OR – February 3, 2026 – Today, The Khronos® Group, an open consortium of industry-leading companies creating graphics and spatial computing standards, announces a release candidate for the KHR_gaussian_splatting baseline extension. This extension enables storing 3D Gaussian splats in glTF® 2.0, the most widely adopted 3D asset delivery format. A release candidate allows for broad industry feedback before ratification to ensure the final specification meets industry needs.
The new extension establishes an open foundation for representing Gaussian splats, an increasingly important geometry and radiance field representation, across real-time graphics, digital twins, and large-scale geospatial visualization pipelines.
“KHR_gaussian_splatting marks a major milestone for glTF, extending the format to support an entirely new class of geometric representation,” said Neil Trevett, president of the Khronos Group. “By bringing the Gaussian splatting community together around a standards-based approach, Khronos is helping ensure this powerful new rendering technique can scale across tools, platforms, and the web.”
Gaussian splatting is a radiance field representation technique that converts multiple 2D images into a photorealistic 3D asset. Photos or videos are used to create a sparse 3D point cloud of an object or scene, with each point defined by properties including position, scale, rotation, color, and opacity. Machine learning optimizes these Gaussian points to match the original input images, and the optimized points are projected onto a 2D surface via rasterization to produce highly responsive camera views.
This approach has proven especially well-suited to geospatial capture workflows, including:
Gaussian splats can be trained quickly, achieve high frame rates, and scale from individual objects to entire urban environments—making them increasingly attractive for mapping, digital twins, infrastructure monitoring, simulation, and situational awareness.
Gaussian splatting is also being quickly adopted in many other markets including photojournalism, media and entertainment, robotics training, cultural preservation, and is poised to bring 3D capture and display to social media. At the same time, generation, training, rendering, and compression techniques continue to evolve and improve.
Without standardization, this rapid evolution could easily lead to fragmentation. In January 2025, the Metaverse Standards Forum initiated a series of public Town Halls to explore whether Gaussian splatting was ready for standardization. Stakeholders identified strong overlap across use cases and interoperability challenges that could be meaningfully addressed through open standards—specifically by enabling splat storage in glTF assets.
A key conclusion was the importance of enabling Gaussian splats to integrate cleanly into existing spatial data ecosystems, where assets must coexist with meshes, terrain, imagery, and sensor-derived data, often within Earth-referenced coordinate systems. Standardizing Gaussian splat storage within glTF was identified as a critical step toward that goal.
The Khronos 3D Formats Working Group responded with a focused development effort and is now gathering a final round of industry input on the resulting KHR_gaussian_splatting glTF extension. Khronos encourages engine developers, implementers, creators, and artists to explore the specification, experiment with sample assets, develop implementations, and share their feedback. Strong community input will help ensure a solid foundation and vocabulary for interoperable, spatially contextualized 3D Gaussian splat content delivered in the glTF format while supporting ongoing innovation.
KHR_gaussian_splatting extends the glTF 2.0 mesh primitive to represent 3D Gaussian splat datasets, including:
This extension allows compatible renderers to interpret primitives as Gaussian splat datasets. This enables import and export of splats as glTF assets using existing tooling pipelines, making it straightforward to share transforms, cameras, and animations. Key capabilities include:
The KHR_gaussian_splatting extension defines uncompressed, GPU-ready data structures for efficient rendering. Because Gaussian splatting techniques are still rapidly evolving, the extension is designed to be algorithm-agnostic and readily extensible. The current specification defines a base ellipsoid kernel, but as the field advances, KHR_gaussian_splatting can adapt to incorporate new kernel types, color spaces, projection methods, and sorting techniques.
For use cases requiring compressed data for efficient transmission, several compression extensions building on KHR_gaussian_splatting have already been proposed, including support for Niantic Spatial’s SPZ and Qualcomm’s L-GSC formats. As glTF is an open and extensible format, any organization can create vendor extensions for additional compression schemes—and propose them for development as a cross-vendor Khronos standard if there is sufficient industry interest and adoption.
Khronos recognizes that the industry will likely go through a period of experimentation with Gaussian splat compression schemes, kernel types, and related topics. To foster constructive dialogue, Khronos will work with the Metaverse Standards Forum to continue the influential Gaussian Splat Town Hall series, providing an open venue for consensus-building and helping avoid unnecessary fragmentation. Khronos also welcomes direct collaboration on splatting adoption and standardization with standards organizations with which it has liaisons, including the Alliance for OpenUSD (AOUSD), the Academy Software Foundation (ASWF), and the UHD World Association (UWA). For example, Khronos and AOUSD are actively coordinating to ensure that glTF extensions and OpenUSD schemas for Gaussian splats remain aligned, enabling seamless conversion between the two standards.
“Our goal is to enable interoperability now while leaving room for innovation,” said Adam Morris, Bentley Systems software engineer and key contributor to the KHR_gaussian_splatting extension. “This flexible design will allow glTF to stay current with the rapid pace of innovation in Gaussian splatting while supporting the widest possible range of use cases.”
Gaussian splatting is production-ready, including on mobile. Bringing splats to glTF makes them even more accessible to researchers, tool developers, and content creators, accelerating the scalable creation and deployment of detailed, interoperable assets, scenes, and worlds.
Examples of early adopter applications planning to use the release candidate KHR_gaussian_splatting extension include CesiumJS, Esri ArcGIS, Niantic Spatial’s Scaniverse, and XGRIDS Lixel Cybercolor.
The KHR_gaussian_splatting extension was developed in response to industry demand, with contributions from leading ecosystem stakeholders including Autodesk, Cesium/Bentley Systems, Esri, Huawei, Niantic Spatial, NVIDIA, and XGRIDS.
“As Gaussian splats become a mainstream content format, frictionless exchange between OpenUSD and glTF will be critical,” said Guy Martin, vice-chair, AOUSD Steering Committee at the Alliance for OpenUSD. “We’re pleased to work alongside Khronos to make that a reality, giving creators confidence that their assets will move smoothly across the entire content lifecycle.”
“Standardizing Gaussian splatting in glTF is a major step forward for the 3D ecosystem,” said Patrick Cozzi, chief platform officer at Bentley Systems and founder of Cesium. “This extension gives developers, creators, and platform providers a common foundation for sharing realistic, real‑world scenes at scale. At Bentley and Cesium, we’ve seen firsthand how Gaussian splats are transforming the capture and visualization of infrastructure and the world around us. This extension will be a key component of the upcoming OGC 3D Tiles 2.0 standard. KHR_gaussian_splatting brings the community together around an open, interoperable approach that will accelerate innovation across industries.”
“This extension is a joint community success laying the foundation for Gaussian Splats as an interoperable asset. As a rich information source, it will serve from visualization to intelligent decision-making in large-scale digital twins.” said Konrad Wenzel, Esri. “For geospatial users, GIS systems like ArcGIS can now consume this along with map data, imagery, or real-time information to empower holistic decision-making—while connecting business platforms seamlessly.”
“Niantic Spatial fully supports this release candidate for a gITF Gaussian Splatting extension as a critical step toward making this transformative format universally available,” said Brian McClendon, CTO, Niantic Spatial. “We have seen firsthand through Scaniverse how Gaussian Splatting is revolutionizing workflows for our enterprise customers, offering an unmatched combination of speed and fidelity. This standardization ensures that these powerful assets can now be deployed seamlessly across the entire 3D ecosystem.”
“Gaussian splatting represents the first real bridge between radiance fields and large-scale industry adoption, spanning construction, geospatial, entertainment, real estate, robotics, automotive, and beyond,” said Michael Rubloff, managing editor, RadianceFields.com. “By providing a shared foundation through KHR_gaussian_splatting, glTF enables this momentum to scale without fragmentation as more industries begin shipping Gaussian splat-based content and products.”
“3D Gaussian graphics technology is advancing at an unprecedented pace, rapidly gaining traction across key sectors, including social sharing, e-commerce, geospatial services, film and content production, and digital twins,” said Wengang Zhang, secretary general of the UWA. “By extending the glTF standard to support 3D Gaussian representations, we can significantly enhance interoperability and enable seamless sharing of 3D content across applications, platforms, and devices. UWA looks forward to collaborating with Khronos to drive the development and widespread adoption of open standards for 3D formats, accelerating innovation and growth across the entire 3D ecosystem.”
“Gaussian splatting has moved beyond research and demos — it is already being used to capture and represent complex real-world environments at scale,” said Kaiyong Zhao, XGRIDS. “For companies like XGRIDS, which deploy 3D Gaussian splatting across large spaces, dynamic environments, and production workflows, a standardized glTF-based representation is critical. KHR_gaussian_splatting provides the foundation needed to integrate Gaussian splats into real-world pipelines while ensuring interoperability across tools and platforms.”
Khronos invites the community to provide feedback and input to help shape the future of Gaussian splatting within glTF. The Khronos 3D Formats Working Group will review all community feedback on KHR_gaussian_splatting before ratification, which is expected in the second quarter of 2026.
Feedback can be provided by adding comments to the Khronos GitHub.
All companies wishing to take an active role in shaping the future of glTF, Gaussian splatting, or any other Khronos standards are welcome to become a member of the Khronos Group and join one or more of the Working Groups that drive our family of open standards. Learn more at khronos.org/members.
###
Khronos® and glTF® are registered trademarks of The Khronos Group Inc. All other product names, trademarks, and/or company names are used solely for identification and belong to their respective owners.
