動画拡散潜在変数からの三角形スプラット生成（5 分読了）

Feedforward Latent Triangle Splatting for geometrically accurate scene generation.

Decode explicit surface-aligned triangle splats from video diffusion latents in a single forward pass.

Orest Kupyn1,2, Goutam Bhat1, Philipp Henzler1, Fabian Manhardt1, Christian Rupprecht1,2, Federico Tombari1,3

1 Google Research

2 University of Oxford, Visual Geometry Group

3 Technical University of Munich

FLAT shows that compressed video diffusion latents can be mapped directly to explicit non-volumetric scene parameters. Instead of decoding 3D Gaussians, it predicts triangle splats in one pass, improving geometric accuracy while preserving competitive visual quality and enabling rasterization with simple triangle renderers and physics-based interaction after lightweight refinement.

Direct Triangle Decoding

FLAT turns compressed video diffusion latents into explicit triangle splats directly, avoiding the usual generate-then-optimize path used by many feedforward scene pipelines.

Geometry-Specific Training

Ray-centered triangle parameterization and a product window rendering function stabilize triangle regression, where small orientation errors would otherwise break gradient flow.

Refinement to Opaque Assets

A lightweight test-time refinement step converts the predicted triangle soup into a fully opaque representation that fits standard rendering and game-engine-style interaction.

Inspect generated scenes as explicit triangle geometry.

FLAT outputs scenes that can be explored immediately with a simple triangle renderer. This makes the viewer fast and portable across devices, without depending on a heavy rendering engine. On touch devices, drag inside the scene to look around and use the on-screen movement buttons to navigate.

White Room

Loading White Room...

Navigation

W A S D move, drag to look, R to reset.

Tip

Double-click anywhere in the viewport to snap back to the default view.

Touch Movement

Appearance and surface structure stay aligned.

We target geometric accuracy, not only image realism. These paired renders show that FLAT's novel views and surface normals stay consistent across viewpoints, making the geometry signal legible instead of hiding it behind appearance alone.

Novel View

Surface Normals

01 / 07

01 / 07

BibTeX

@misc{kupyn2026flat,
  title        = {FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation},
  author       = {Orest Kupyn and Goutam Bhat and Philipp Henzler and Fabian Manhardt and Christian Rupprecht and Federico Tombari},
  year         = {2026},
  note         = {Preprint}
}