解决2D高斯点阵在反光表面的漏洞问题，提升重建精度。
Introducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstruction
- 引入深度偏置修正反射跳变，优化高斯原型深度
- 新深度收敛损失使表面深度连续性更强
- 适合需要高精度表面重建的应用场景
近期，2D高斯点阵（2DGS）通过使用2D泡状体近似薄表面，在几何重建质量上优于主流的3DGS。然而，在处理反光表面时仍存在明显孔洞。我们发现这是由反射不连续性导致的。为拟合不同视角下漫反射到镜面反射的跃变，我们在优化的高斯原型中引入深度偏置。为此，首先将2DGS中的深度扭曲损失替换为一种新型深度收敛损失，强化深度连续性的约束；其次，修正射线中确定真实表面的深度准则，充分考虑所有相交高斯体的影响。在多个数据集上的定性和定量评估表明，本方法显著提升了重建质量，表面更完整、更准确。代码已公开于 https://github.com/XiaoXinyyx/Unbiased_Surfel。
原文摘要 · Abstract (English)
Recently, 2D Gaussian Splatting (2DGS) has demonstrated superior geometry reconstruction quality than the popular 3DGS by using 2D surfels to approximate thin surfaces. However, it falls short when dealing with glossy surfaces, resulting in visible holes in these areas. We find that the reflection discontinuity causes the issue. To fit the jump from diffuse to specular reflection at different viewing angles, depth bias is introduced in the optimized Gaussian primitives. To address that, we first replace the depth distortion loss in 2DGS with a novel depth convergence loss, which imposes a strong constraint on depth continuity. Then, we rectify the depth criterion in determining the actual surface, which fully accounts for all the intersecting Gaussians along the ray. Qualitative and quantitative evaluations across various datasets reveal that our method significantly improves reconstruction quality, with more complete and accurate surfaces than 2DGS. Code is available at https://github.com/XiaoXinyyx/Unbiased_Surfel.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。