Table of Contents
Fetching ...

Texel Splatting: Perspective-Stable 3D Pixel Art

Dylan Ebert

Abstract

Rendering 3D scenes as pixel art requires that discrete pixels remain stable as the camera moves. Existing methods snap the camera to a grid. Under orthographic projection, this works: every pixel shifts by the same amount, and a single snap corrects all of them. Perspective breaks this. Pixels at different depths drift at different rates, and no single snap corrects all depths. Texel splatting avoids this entirely. Scene geometry is rendered into a cubemap from a fixed point in the world, and each texel is splatted to the screen as a world-space quad. Cubemap indexing gives rotation invariance. Grid-snapping the origin gives translation invariance. The primary limitation is that a fixed origin cannot see all geometry; disocclusion at probe boundaries remains an open tradeoff.

Texel Splatting: Perspective-Stable 3D Pixel Art

Abstract

Rendering 3D scenes as pixel art requires that discrete pixels remain stable as the camera moves. Existing methods snap the camera to a grid. Under orthographic projection, this works: every pixel shifts by the same amount, and a single snap corrects all of them. Perspective breaks this. Pixels at different depths drift at different rates, and no single snap corrects all depths. Texel splatting avoids this entirely. Scene geometry is rendered into a cubemap from a fixed point in the world, and each texel is splatted to the screen as a world-space quad. Cubemap indexing gives rotation invariance. Grid-snapping the origin gives translation invariance. The primary limitation is that a fixed origin cannot see all geometry; disocclusion at probe boundaries remains an open tradeoff.
Paper Structure (10 sections, 1 equation, 2 figures)

This paper contains 10 sections, 1 equation, 2 figures.

Figures (2)

  • Figure 1: Texel splatting renders 3D scenes as perspective-stable pixel art. Each cubemap texel is splatted to screen as a world-space quad that remains fixed to geometry as the camera moves.
  • Figure 2: Pipeline overview. Each column pairs an orthographic diorama (top) with the corresponding camera view (bottom). The white dot marks the probe origin; the wireframe shows the camera frustum. (a) Scene geometry rasterized from the probe origin. (b) Cubemap captured around the probe. (c) Visible texels splatted as world-space quads.