用信心融合提升稀疏视角下的3D重建质量
Pseudo-View Enhancement via Confidence Fusion for Unposed Sparse-View Reconstruction
- 双向伪视图恢复，利用相邻帧引导扩散生成
- 通过深度-密度联合优化高斯点，减少漂浮伪影
- 适合户外稀疏视角重建，效果稳定且几何一致
在无固定视角的稀疏视点条件下进行3D场景重建是一个极具挑战性但实际应用重要的问题，尤其在户外场景中，由于光照复杂和尺度变化大，重建难度更高。输入视点极度稀少时，直接使用扩散模型合成伪图像会引入不合理几何结构，损害最终重建质量。为此，我们提出一种新型框架，通过双向伪视图恢复与场景感知高斯管理实现高质量重建。具体而言，设计了一种基于扩散的双向伪视图恢复方法，利用相邻帧引导扩散生成缺失内容，并结合轻量级伪视图去模糊模型与置信度掩码推断算法。随后提出场景感知高斯管理策略，基于深度-密度联合信息优化高斯点。该设计显著提升了重建完整性，抑制了漂浮伪影，并改善了极端视点稀疏条件下的整体几何一致性。在多个户外基准数据集上的实验表明，本方法在保真度和稳定性方面均显著优于现有方法。
原文摘要 · Abstract (English)
3D scene reconstruction under unposed sparse viewpoints is a highly challenging yet practically important problem, especially in outdoor scenes due to complex lighting and scale variation. With extremely limited input views, directly utilizing diffusion model to synthesize pseudo frames will introduce unreasonable geometry, which will harm the final reconstruction quality. To address these issues, we propose a novel framework for sparse-view outdoor reconstruction that achieves high-quality results through bidirectional pseudo frame restoration and scene perception Gaussian management. Specifically, we introduce a bidirectional pseudo frame restoration method that restores missing content by diffusion-based synthesis guided by adjacent frames with a lightweight pseudo-view deblur model and confidence mask inference algorithm. Then we propose a scene perception Gaussian management strategy that optimize Gaussians based on joint depth-density information. These designs significantly enhance reconstruction completeness, suppress floating artifacts and improve overall geometric consistency under extreme view sparsity. Experiments on outdoor benchmarks demonstrate substantial gains over existing methods in both fidelity and stability.
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。