02·3D & Spatial
3DGS Research Pipeline
Applied 3D Gaussian Splatting research pipeline. Covers scanned interiors, AI-generated scenes for unbuilt properties (video diffusion, novel-view synthesis, monocular depth), and city-scale capture. Twenty-two engines benchmarked across 56 evaluations.
What it took
The skills behind this project.
Every project below leans on a primary discipline and a handful of secondary ones. Tap any chip to see how that skill plays out across the wider portfolio.
Skills demonstrated
- ResearchPrimary
22 3DGS engines benchmarked across 56 evaluations spanning studio scans to city-scale capture.
- 3D & SpatialSecondary
Novel-view synthesis and monocular depth paths for unbuilt properties stitched into the same pipeline.
- AI & Machine LearningSecondary
Video-diffusion novel-view models evaluated against COLMAP-grounded baselines.
- Data PipelinesSupporting
Reproducible eval harness across PSNR, SSIM, and per-engine failure modes.
Context
Why it exists.
3D Gaussian Splatting moved fast between 2023 and 2026. New engines shipped every quarter, each claiming higher PSNR on their preferred benchmark scenes. The applied question — which one actually survives a luxury real-estate brief, on a real scanner, in a real building — sat unanswered.
This pipeline answers it. Twenty-two engines benchmarked across fifty-six evaluations, spanning the full difficulty range from a clean scan-studio booth through a mirror-walled marble lobby to a city-scale neighbourhood capture. Not just average quality — robustness, with failure modes per engine logged, because an engine that crashes on one scan in five is unusable in production regardless of its PSNR on the other four.
The pipeline also covers the unbuilt case: novel-view synthesis via video diffusion, monocular depth lift, and the hybrid stack that bolts those onto a real scan when only half a building has been constructed.
StackCUDA · gsplat · PyTorch · COLMAP · Video diffusion · Monocular depth
Process
The decisions that shaped it.
- 01
Three difficulty bands, not one leaderboard
Most 3DGS benchmarks score against a small set of scene types — usually clean studio scans where every modern engine clears thirty dB. Split the eval into seven scan-difficulty bands from Easy Scan-Studio through Extreme Commercial-Office, so engines that excel at clean interiors but fail on mirrored marble are scored honestly. Choice of engine matters more than expected at the easy end too.
Research - 02
Failure mode is a first-class metric
Engines do not just produce worse images on hard scenes — they crash, produce floaters, or output garbage point clouds that crash downstream rendering. Logged every fail as a red cell in the per-engine × per-scan heatmap. The SIGGRAPH submission leads with this matrix, not the PSNR scores, because robustness is what a production team buys.
Data Pipelines - 03
Novel-view synthesis as a parallel path
Off-plan luxury properties have no scan to start from — the building has not been built. Ran video diffusion and monocular depth lift in parallel to the scanned pipeline, so the same viewer can show a real apartment and an AI-imagined one without two separate codebases. The eval covers both paths against COLMAP-grounded baselines.
AI & Machine Learning - 04
Cleaned vs raw as a routine comparison
Floaters and stray gaussians make scans look worse than the underlying capture warrants. Every scan in the eval was run twice — raw output and after a cleaning pass — to quantify how much of the quality delta is the engine versus the post-processing. Cleaning recovers roughly eight per cent of noisy gaussians on average, and changes which engine wins on the hardest scenes.
3D & Spatial
Outcome
What shipped.
Submitted to SIGGRAPH Asia 2026 (Tech Communications track) on applied 3DGS in luxury real-estate visualisation.
Submitted to SIGGRAPH Asia 2026 (Tech Communications track) in May. The eval framework continues to run on new engines as they ship — adding a row to the heatmap is a one-day operation now. The pipeline directly informs which engine ships behind the Splat Viewer for each property type.