用三平面加速3D重建，3张图就能高质量生成遥感新视角。
TriDF: Triplane-Accelerated Density Fields for Few-Shot Remote Sensing Novel View Synthesis
- 分色与密度独立建模，结合三平面结构提速收敛。
- 相比NeRF快30倍，PSNR提升7.4%，SSIM提升3.4%。
- 适合少样本遥感场景，抗过拟合，适合城市规划应用。
遥感新视角合成（NVS）在城市规划和环境监测中具有重要潜力，但受限于多视角图像获取困难，常面临输入视图不足的问题。现有方法在少样本情况下易过拟合，而先进方法计算开销大且在遥感场景表现不佳。本文提出TriDF，一种高效的混合3D表示方法，仅需3个输入视图即可实现快速遥感新视角合成。该方法将颜色与体密度信息解耦建模，降低隐式辐射场的计算负担并加速重建。通过将高频颜色信息映射至紧凑的三平面结构，并直接优化特征平面，显著加快收敛速度。体密度以连续密度场建模，利用基于图像渲染的邻近视图参考特征弥补数据不足。此外，引入基于点云的深度引导优化，有效缓解少样本下的过拟合问题。在多个遥感场景上的实验表明，该方法相比基于NeRF的方法提升30倍速度，同时在渲染质量上优于先进少样本方法（PSNR提升7.4%，SSIM提升3.4%）。代码已开源：https://github.com/kanehub/TriDF。
原文摘要 · Abstract (English)
Remote sensing novel view synthesis (NVS) offers significant potential for 3D interpretation of remote sensing scenes, with important applications in urban planning and environmental monitoring. However, remote sensing scenes frequently lack sufficient multi-view images due to acquisition constraints. While existing NVS methods tend to overfit when processing limited input views, advanced few-shot NVS methods are computationally intensive and perform sub-optimally in remote sensing scenes. This paper presents TriDF, an efficient hybrid 3D representation for fast remote sensing NVS from as few as 3 input views. Our approach decouples color and volume density information, modeling them independently to reduce the computational burden on implicit radiance fields and accelerate reconstruction. We explore the potential of the triplane representation in few-shot NVS tasks by mapping high-frequency color information onto this compact structure, and the direct optimization of feature planes significantly speeds up convergence. Volume density is modeled as continuous density fields, incorporating reference features from neighboring views through image-based rendering to compensate for limited input data. Additionally, we introduce depth-guided optimization based on point clouds, which effectively mitigates the overfitting problem in few-shot NVS. Comprehensive experiments across multiple remote sensing scenes demonstrate that our hybrid representation achieves a 30x speed increase compared to NeRF-based methods, while simultaneously improving rendering quality metrics over advanced few-shot methods (7.4% increase in PSNR and 3.4% in SSIM). The code is publicly available at https://github.com/kanehub/TriDF
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。