Hexels improve 3D scene rendering and reconstruction efficiency
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Computer Vision and Pattern RecognitionArtificial IntelligenceGraphicsMachine Learning
Summary
Generating 3D scenes and new views from images usually needs a lot of computer memory and power. The authors introduce hexels, which are hexagonal surface pieces that can represent color changes smoothly and use fewer parts to show a scene. These hexels are more memory-efficient and faster to train than previous methods, and they improve image quality when rendering or reconstructing 3D surfaces. They also work well for 2D images, offering a better balance between quality and efficiency.
What this means in practice
- •For graphics engineers: Improve 3D scene rendering quality and speed while reducing memory use by incorporating hexagonal surface elements.
- •For visual effects studios: Create more efficient 3D reconstructions for complex scenes, enabling higher quality outputs with fewer computational resources.
Authors
Prakhar Kaushik, Soumava Paul, Alan Yuille
Abstract
Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal surface elements with a first-order spatial color field for efficient 3D scene and 2D image representation. Hexels exploit locally planar regions with smoothly varying appearance using fewer, larger primitives. Their hexagonal support provides an area- and boundary-efficient domain, while the local color field captures appearance variation within each primitive. Across 34 scenes, Hexels improve PSNR over memory-matched 2DGS by 4.53-7.38 dB across datasets while requiring lower training VRAM. We further ablate Hexels by showing that per primitive, Hexels outperform 2DGS by upto 4.74 dB while using lower training VRAM and having 2.31 times faster FPS. Even in unconstrained settings, Hexels offers complementary quality-memory trade-offs. For efficient 3D surface reconstruction, Hexels reduce error by 28.9% compared with memory-matched 2DGS across 15 DTU scans. On 6 Tanks and Temples surface scenes, Hexels achieves the highest mean F1 among compared methods (34.38%, versus 31.72% for 2DGS). We further also show that Hexels, as a general primitive, improves 2D image representation over Image-GS. Hexels push the Pareto frontier on the quality-efficiency trade-off of surface-aligned primitives.