发表机构
Beihang University（北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出DIBR-GS，利用深度图像渲染生成伪视图进行跨视角监督，解决遥感稀疏视角下3DGS的几何约束不足问题，仅用3个输入视图即显著提升重建质量。
AI 中文摘要
在稀疏观测条件下，遥感新视角合成由于几何约束不足和跨视角监督有限而仍然具有挑战性。现有的神经辐射场（NeRF）和三维高斯泼溅（3DGS）方法容易过拟合，并面临深度模糊、跨视角信息缺失以及观测不足区域约束不足的问题。为解决这些挑战，我们提出了DIBR-GS，一种利用深度图像渲染（DIBR）生成伪视图以进行跨视角一致性监督的神经高斯泼溅框架。具体而言，通过将单目深度先验与稀疏SfM重建对齐来构建可靠的几何初始化，并将跨视角外观先验融入神经高斯表示，以增强稀疏观测下的外观建模。此外，我们引入了一种渐进式基于DIBR的伪视图监督策略，以提供额外的几何和外观约束，从而实现对弱观测区域的更完整重建。另外，设计了一种高度约束的锚点增长策略，以抑制不合理的高斯扩展。实验表明，在仅使用3个输入视图进行训练时，所提出的方法优于现有方法。与之前最佳方法相比，PSNR提高了6.83 dB，SSIM相对提升14%，LPIPS相对提升60%，同时保持了有竞争力的计算效率。我们的代码可在该https URL获取。
英文摘要
Remote sensing novel view synthesis under sparse observations remains challenging due to insufficient geometric constraints and limited cross-view supervision. Existing Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) methods are prone to overfitting and face challenges of depth ambiguities, missing cross-view information, and insufficient constraints in under-observed regions. To address these challenges, we propose DIBR-GS, a neural Gaussian Splatting framework that exploits Depth Image-Based Rendering (DIBR) to generate pseudo views for cross-view consistency supervision. Specifically, reliable geometric initialization is constructed by aligning monocular depth priors with sparse SfM reconstruction, and cross-view appearance priors are incorporated into neural Gaussian representations to enhance appearance modeling under sparse observations. Furthermore, we introduce a progressive DIBR-based pseudo-view supervision strategy to provide additional geometric and appearance constraints, enabling more complete reconstruction of weakly observed regions. In addition, a height-constrained anchor growth strategy is designed to suppress unreasonable Gaussian expansion. Experiments demonstrate that the proposed method achieves superior performance over existing approaches when training with only 3 input views. Compared with the previous best-performing method, it improves PSNR by 6.83 dB, with relative gains of 14\% in SSIM and 60\% in LPIPS, while maintaining competitive computational efficiency. Our code is available at https://github.com/kanehub/DIBR-GS
