ManifoldNeuS：流形感知的视图可优化性用于无位姿神经表面重建
ManifoldNeuS: Manifold-aware View Optimizability for Pose-Free Neural Surface Reconstruction
提出流形感知的视图可优化性分数（MaVOS），用于动态调度视图、门控位置编码和抗分数损失加权，可迁移到其他需要联合优化相机位姿与场景表示的视觉任务中。
原文依据 we propose ManifoldNeuS, a novel method that explicitly models and leverages per-view optimizability to guide pose-free neural surface reconstruction.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从无位姿图像中联合优化相机位姿和物体几何是神经表面重建中的一项挑战性任务。现有方法常受位姿漂移和几何扭曲的困扰，根源在于易视图偏差——均匀视图优化偏向于纹理丰富、重叠良好且主导梯度更新的易优化视图，而纹理微弱或重叠有限但对几何完整性至关重要的难优化视图则逐渐被边缘化。为解决此问题，我们提出ManifoldNeuS，一种新颖的方法，显式建模并利用逐视图可优化性来引导无位姿神经表面重建。具体而言，我们引入流形感知视图可优化性分数（MaVOS），该分数在视图一致的流形上联合评估即时适应度（优化每个视图的难易程度）和长期覆盖增益（优化每个视图的价值）。基于MaVOS，我们进一步设计了一个重建流程，将逐视图可优化性作为状态控制信号，通过三个关键组件引导联合优化过程：动态视图调度、门控位置编码和抗分数损失加权。在基准数据集上的实验结果表明，ManifoldNeuS在准确姿态估计和高质量重建方面优于现有方法，在未知相机位姿的情况下实现了鲁棒的联合优化。
英文原文摘要 1461 字符
Jointly optimizing camera poses and object geometry from unposed images is a challenging task in neural surface reconstruction. Existing methods often suffer from pose drift and geometric distortion, stemming from the easy-view bias --- uniform view optimization favors easy-to-optimize views with abundant texture and good overlap that dominate gradient updates, while hard-to-optimize counterparts with weak texture or limited overlap yet critical for geometric completeness are progressively marginalized. To address this, we propose ManifoldNeuS, a novel method that explicitly models and leverages per-view optimizability to guide pose-free neural surface reconstruction. Specifically, we introduce the manifold-aware view optimizability score (MaVOS), which jointly assesses immediate fitness (the ease of optimizing each view) and long-term coverage gain (the value of optimizing each view) over the view-coherent manifold. Building on the MaVOS, we further devise a reconstruction pipeline that incorporates the per-view optimizability as a state control signal to guide the joint optimization process through three key components: dynamic view scheduling, gated positional encoding, and anti-score loss weighting. Experimental results on the benchmark dataset demonstrate that ManifoldNeuS outperforms existing methods in terms of accurate pose estimation and high-quality reconstruction, achieving robust joint optimization without known camera poses.