用虚拟相机采样和扩散模型增强3D高斯重建，实现任意视角无瑕疵渲染。
ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors
- 通过信息增益策略自动规划虚拟相机位置，覆盖更多场景区域。
- 结合视频扩散先验优化渲染结果，使远偏离视角的图像更清晰。
- 适用于需要自由探索的3D场景应用，如虚拟现实与数字孪生。
最近的新型视图合成（NVS）进展使得基于3D高斯点阵（3DGS）实现实时渲染成为可能。然而，现有方法在偏离训练轨迹的视角下仍存在伪影和缺失区域，限制了无缝场景探索。为此，我们提出一种基于3DGS的管道，通过生成额外训练视图来提升重建质量。引入基于信息增益的虚拟相机放置策略以最大化场景覆盖，并利用视频扩散先验对渲染结果进行精细化处理。使用这些增强视图微调3D高斯点阵显著提升了重建质量。为评估该方法，我们构建了Wild-Explore基准，用于挑战性场景探索测试。实验表明，本方法优于现有3DGS基线，在任意视角下均能实现高质量、无伪影的渲染。
原文摘要 · Abstract (English)
Recent advances in novel view synthesis (NVS) have enabled real-time rendering with 3D Gaussian Splatting (3DGS). However, existing methods struggle with artifacts and missing regions when rendering from viewpoints that deviate from the training trajectory, limiting seamless scene exploration. To address this, we propose a 3DGS-based pipeline that generates additional training views to enhance reconstruction. We introduce an information-gain-driven virtual camera placement strategy to maximize scene coverage, followed by video diffusion priors to refine rendered results. Fine-tuning 3D Gaussians with these enhanced views significantly improves reconstruction quality. To evaluate our method, we present Wild-Explore, a benchmark designed for challenging scene exploration. Experiments demonstrate that our approach outperforms existing 3DGS-based methods, enabling high-quality, artifact-free rendering from arbitrary viewpoints. https://exploregs.github.io
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。