๐ค AI Summary
This work addresses the limitations of Gaussian-Enhanced Surfels (GES) in order-free rendering, which often suffer from aliasing and insufficient reconstruction quality. The authors propose DP-GES, a novel surfel representation that introduces semi-transparent boundaries and leverages depth peeling to establish pixel-accurate ordering without explicit sorting. This approach enables high-fidelity Gaussian splatting while supporting correct transmission modulation and fully differentiable joint optimizationโthe first such capability within an order-free framework. By doing so, DP-GES effectively eliminates aliasing and flickering artifacts. Experimental results demonstrate that DP-GES significantly outperforms current state-of-the-art methods across diverse scenes, achieving markedly improved reconstruction fidelity.
๐ 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.