研究人员开发了一种新方法，以提高3D高斯泼溅（3DGS）在仅用有限视图进行训练时的泛化能力。通过应用平坦最小值优化的原理，该技术通过考虑各向异性和训练进度的受控扰动来正则化高斯参数。这种方法有助于保留精细细节并增强对过拟合的鲁棒性，从而实现更清晰、更稳定的重建，并能更好地泛化到新的视角，这在LLFF和Mip-NeRF360数据集上得到了证明。 AI
影响 提高了神经渲染技术在3D场景重建中的鲁棒性和泛化能力。
排序理由 详细介绍计算机视觉模型新优化技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.00885v1 Announce Type: cross Abstract: Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity. However, when su…
Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity. However, when supervision is limited to sparse input views, 3DGS t…