Conversion guide

Point Cloud to Gaussian Splat Conversion

A point cloud can provide strong geometric initialization, but geometry alone is not the same as a view-synthesis dataset. Useful conversion depends on RGB observations, camera poses, scan alignment and scene coverage.

Use the E57 conversion service Review requirements

Feasibility

When conversion is possible

The strongest source package combines measured geometry with calibrated appearance observations.

Point geometry

Positions provide scene structure and can seed Gaussian locations. Density, noise and coordinate alignment affect the initialization.

RGB information

Per-point color can help, but projected color alone may not contain enough multi-view appearance to render novel viewpoints accurately.

Source imagery

Overlapping photos or panoramas provide the observations used to optimize appearance across viewpoints. Consistent exposure and sharpness help.

Camera poses

Camera intrinsics and positions/orientations connect each image to the scene. Missing or inaccurate poses make training unreliable.

Color and appearance

How point-cloud RGB values are used in Gaussian splatting

Point-cloud RGB values record red, green and blue color samples alongside measured XYZ positions. They describe the color observed at those points, rather than a complete model of how a surface looks from every viewpoint.

In the existing e57.gs workflow, point geometry supplies spatial structure and available RGB supplies source color information. When compatible scanner imagery and station poses are present, full training uses those observed views to optimize the Gaussian scene and its appearance. Color consistency, exposure and capture coverage affect the result.

A colored point cloud stores spatial samples with color attributes. A Gaussian Splat scene uses primitives with size, orientation, opacity and appearance attributes that blend during rendering. Training can refine those attributes for new viewpoints; copying RGB values or changing a file extension does not perform that optimization or recover unobserved surfaces.

Containers

E57, LAS, LAZ and PLY are not equivalent inputs

Format	Common contents	e57.gs automated status
E57	Aligned scan positions, points, color and sometimes imagery or pose-related data	Accepted by the automated account upload
LAS / LAZ	LiDAR points, classification, intensity and optional RGB; LAZ is compressed	Not advertised as a direct automated input
PLY	Flexible point, mesh or Gaussian attributes; schema varies widely	Not advertised as a direct automated input

Inside E57: E57 is a container rather than a simple XYZ list. It stores measured point data in data3D and may also include color, embedded imagery, and camera or pose-related information in images2D. Export contents vary, so the file extension alone does not guarantee that usable imagery or camera information is present.

For LAS, LAZ or point-cloud PLY, prepare a supported E57 package with scan positions aligned in one coordinate system where appropriate, or request a feasibility review. Renaming an extension does not convert the underlying data.

Output quality

Initialization is only the beginning

Gaussian optimization can refine a scene representation, but it cannot create trustworthy detail for surfaces and viewpoints absent from the capture.

Dense, correctly aligned geometry can stabilize structure but does not replace image observations.
Sparse viewpoints create holes, floaters or unstable appearance at novel angles.
Reflective, transparent or moving surfaces can violate the assumptions of a static scene.
A completed result must be visually inspected; it is not certified survey or engineering data.

Deliverables

Choose output by viewer and tool support

Gaussian PLY

Useful for compatible Gaussian-Splat editors and interchange workflows. A normal point-cloud PLY and a Gaussian PLY are not interchangeable merely because both use .ply.

SPLAT

A compact distribution format used by compatible web viewers. It may omit attributes needed by editing tools, so keep the richer output when available.

ArcGIS compatibility

Gaussian splats and ArcGIS: what formats are supported?

A standalone Gaussian PLY cannot be used directly as a Gaussian Splat Layer in ArcGIS Pro. Esri describes a valid splat-authored 3D Tiles dataset referenced by a top-level tileset.json. See Esri's official format guidance.

Need ArcGIS support for your Gaussian Splat workflow? Contact us with your ArcGIS product and version, source format and intended use so we can review your compatibility and delivery requirements. ArcGIS-specific support is subject to review; e57.gs does not currently advertise automatic export of an ArcGIS-ready 3D Tiles package.

Working with a Matterport Pro3 export?

Use the dedicated workflow for a Matterport E57 and see what the converter checks before processing.

Matterport Pro3 E57 to Gaussian Splat

FAQ

Point-cloud conversion questions

Can every point cloud become a Gaussian Splat?

No. Geometry alone can initialize a scene, but high-quality view synthesis also needs suitable color observations, coverage and camera information. Sparse, uncolored or noisy scans have stricter limits.

How are point-cloud RGB values used in Gaussian splatting?

RGB values describe the color sampled at each measured point. In the existing E57 workflow, geometry supplies spatial structure and available RGB supplies source color information. Compatible scanner imagery and station poses support appearance optimization during full training. A Gaussian Splat also represents size, orientation, opacity and appearance; it is not simply an XYZ point with an RGB value.

Does e57.gs accept LAS, LAZ or PLY directly?

The automated e57.gs upload currently accepts E57. LAS, LAZ and PLY are not advertised as direct automated inputs; they may need preparation into a supported E57 package or a feasibility review.

Why do camera poses matter?

Camera poses connect each image observation to a viewpoint in 3D space. Without reliable poses, a training pipeline cannot consistently assign appearance to the scene from multiple views.

What limits output quality?

Missing viewpoints, occlusion, motion, reflective surfaces, low-resolution color, scan-alignment errors, noise and large changes in exposure can all create gaps or artifacts.

Start with a supported E57

The automated service accepts E57. Check that your export includes aligned point geometry and the best available color or image data.

Explore E57 to Gaussian Splat