Extracting Depth From Any Pretrained 3DGS (No Retraining Needed)

Did you know that you can extract perfect depth maps from any pretrained 3D Gaussian Splatting without retraining, depth loss, or special regularizers?

This works because a 3DGS renderer doesn't have to splat colors—it can splat anything. Colors are just one example. If you instead splat the z-value of each Gaussian in camera coordinates, the renderer naturally produces a dense depth map.

RGB vs extracted depth from 3DGS

3D Gaussian Splatting Pioneer: Pulsar

The Pulsar paper (Lassner et al., 2020) —the method that inspired the tile-based apporach in 3DGS— used exactly this idea: instead of splatting RGB, they splatted feature vectors. Afterwards, a CNN decoded the feature map into a final color image.

3DGS uses the same principle. A Gaussian splat is just a weighted blend of attributes:

# A Gaussian contributes:
weight * attribute
    

If the attribute is RGB → you get an RGB image. If the attribute is depth → you get a depth image. If the attribute is normals, albedo, semantics, features → those work too.

How to Extract Depth in PyTorch (5 Lines)

Once you have the per-Gaussian center in camera coordinates pc, just splat pc[:, 2].

# pc: [N, 3] Gaussian centers in camera space
z_depth = pc[:, 2]  # positive forward

# Instead of color = gaussian_color, we replace it with:
attribute = z_depth

# Then call your existing tiling + splatting code:
rendered_depth = splat(attribute, weights, tiles)
    

Because 3DGS uses the exact same weights regardless of attribute type, depth is rendered with the same quality and density as color.

Advantages of This Method

What Else Can We Splat?

Anything.

Remember: 3DGS is just a differentiable splat pipeline. The attributes are completely user-defined.

Learn 3DGS Step-by-Step

📘 Master 3D Gaussian Splatting

Want to go deeper and fully understand how splatting works? My 3D Gaussian Splatting Course explains the entire pipeline from scratch, using PyTorch only, no C++ or CUDA!

Explore the Course →

Consulting

💼 Research & Engineering Consulting

We help teams integrate 3D Gaussian Splatting techniques, build custom pipelines, and prototype new splatting research. If you need expertise, we can help.

Contact:
contact@qubitanalytics.be