CoherentRaster: Efficient 3D Gaussian Splatting for Light Field Displays
Gyujin Sim, Seungjoo Shin, Hosung Jeon, Gwangsoon Lee, Hyon-Gon Choo, Sunghyun Cho

TL;DR
CoherentRaster is a novel 3D Gaussian Splatting framework that enables real-time, high-quality light field display rendering by reducing redundant computation and improving memory efficiency.
Contribution
It introduces Cross-view Coherent Attribute Reuse and View-coherent Remapping to optimize 3D Gaussian Splatting for light field displays.
Findings
Achieves real-time rendering on consumer hardware.
Reduces computational overhead compared to prior methods.
Maintains high-quality light field synthesis.
Abstract
Light field displays (LFDs) require rendering an interlaced image that encodes many view-dependent observations. This multi-view requirement introduces substantial computational overhead, making real-time rendering difficult to achieve. While 3D Gaussian Splatting (3DGS) is efficient for single-view rendering on 2D displays, directly extending it to LFDs is computationally expensive. Moreover, prior accelerations either suffer from GPU inefficiency under spatially incoherent subpixel layouts or rely on computationally heavy multi-plane intermediates. In this paper, we propose CoherentRaster, a 3DGS-based light field rendering framework that performs subpixel-level rasterization. Our method employs Cross-view Coherent Attribute Reuse to eliminate redundant computation across neighboring viewpoints and applies View-coherent Remapping to restore warp-level memory efficiency degraded by the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
