Depth Peeling for High-Fidelity Gaussian-Enhanced Surfel Rendering
2026-05-25 • Graphics
GraphicsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors improved a method for creating new views of 3D scenes from images by enhancing an existing technique called Gaussian-Enhanced Surfels (GES). They added semi-transparent edges and used a process called Depth Peeling to correctly layer the scene without needing to sort everything manually. This helps remove common visual errors like aliasing and sudden changes in the image, resulting in smoother and more accurate 3D reconstructions. Their approach also allows easy optimization of the model and outperforms previous methods in many different scenes.
Novel View SynthesisNeRF3D Gaussian SplattingGaussian-Enhanced SurfelsDepth PeelingVolume RenderingPer-pixel OrderingAliasing ArtifactsDifferentiable OptimizationTransmittance Modulation
Authors
Keyang Ye, Hongzhi Wu, Kun Zhou
Abstract
Novel view synthesis has been significantly advanced by NeRFs and 3D Gaussian Splatting (3DGS), which require ordering volumetric samples or primitives for correct color blending. While the recent Gaussian-Enhanced Surfels (GES) enable high-performance, sort-free rendering, they suffer from aliasing artifacts and suboptimal reconstruction. To address these limitations, we propose DP-GES, a novel representation that augments opaque surfels with semi-transparent boundaries and leverages Depth Peeling to establish accurate per-pixel ordering. This design enables sort-free Gaussian splatting with correct transmittance modulation, effectively eliminating aliasing and popping artifacts while facilitating a fully differentiable joint optimization. Extensive experiments demonstrate that our method achieves superior reconstruction quality and compares favorably against state-of-the-art techniques across a wide range of scenes.