HDGS: Textured 2D Gaussian Splatting for Enhanced Scene Rendering
This work addresses rendering challenges in neural scene reconstruction for applications like virtual reality or graphics, but it appears incremental as it builds directly on 2D Gaussian Splatting.
The paper tackled the problem of rendering fine details and reducing aliasing in 2D Gaussian Splatting for scene rendering by aligning surfels with texture maps and using per-ray depth sorting and frustum-based sampling. The result showed improved detail preservation and anti-aliasing, surpassing existing techniques on benchmarks and a custom dataset.
Recent advancements in neural rendering, particularly 2D Gaussian Splatting (2DGS), have shown promising results for jointly reconstructing fine appearance and geometry by leveraging 2D Gaussian surfels. However, current methods face significant challenges when rendering at arbitrary viewpoints, such as anti-aliasing for down-sampled rendering, and texture detail preservation for high-resolution rendering. We proposed a novel method to align the 2D surfels with texture maps and augment it with per-ray depth sorting and fisher-based pruning for rendering consistency and efficiency. With correct order, per-surfel texture maps significantly improve the capabilities to capture fine details. Additionally, to render high-fidelity details in varying viewpoints, we designed a frustum-based sampling method to mitigate the aliasing artifacts. Experimental results on benchmarks and our custom texture-rich dataset demonstrate that our method surpasses existing techniques, particularly in detail preservation and anti-aliasing.