Abstract:

To address the imbalance between efficiency and accuracy in Neural implicit Surface （NeuS） reconstruction caused by dense sampling and volumetric rendering， a fast and efficient reconstruction method was proposed. Firstly， dynamic occupancy grids were combined with density thresholds to optimize and select effective sampling points， thereby reducing redundant computation and memory usage. Then， multi-resolution hash encoding was integrated with Truncated Signed Distance Field （TSDF） to enhance gradient stability and noise resistance ability through truncated distance constraint and hash feature interpolation. Finally， photometric consistency constraint was introduced to optimize across-view geometric consistency using Normalized Cross-Correlation （NCC）， thereby improving the quality of surface reconstruction. Experimental results show that on the synthetic dataset NeRF-Synthetic， the proposed method reduces the training time by 98.8% compared to Neural Radiance Field （NeRF）. Although the training time of the proposed method is longer than that of Instant-NGP （Instant Neural Graphics Primitives） accelerated by CUDA （Compute Unified Device Architecture）， it achieves significantly superior surface reconstruction quality. On the real dataset DTU， the method achieves a surface reconstruction Chamfer Distance （CD） and a new-view synthesis Peak Signal-to-Noise Ratio （PSNR） significantly better than most existing methods， with CD reduced by 1.21 mm and PSNR higher by 2.93 dB compared to Instant-NGP. Though the metrics of the proposed method are slightly worse than Neuralangelo （with CD higher by 0.02 mm and PSNR lower by 2.05 dB）， the training time of the proposed method is reduced by 97.5% compared to Neuralangelo. It can be seen that this method can improve training efficiency and ensure reconstruction accuracy effectively with good practicality， and is suitable for efficient 3D reconstruction in complex structural scenes.

Key words: Neural implicit Surface (NeuS), 3D reconstruction, Truncated Signed Distance Field (TSDF), dynamic occupancy grid, photometric consistency constraint

摘要：

针对隐式神经表面（NeuS）重建中密集采样及体积渲染导致的效率与精度失衡问题，提出一种快速高效的重建方法。首先，采用动态占用网格结合密度阈值的方法来优化筛选有效采样点，从而降低冗余计算和内存占用；其次，融合多分辨率哈希编码和截断符号距离场（TSDF），以通过截断距离约束和哈希特征插值来增强梯度稳定性与抗噪能力；最后，引入光度一致性约束来利用归一化交叉相关（NCC）优化跨视角几何一致性，从而提高表面重建的质量。实验结果表明：在仿真数据集Nerf-Synthetic上，所提方法的训练时间相较于神经辐射场（NeRF）缩短了98.8%；虽比采用CUDA （Compute Unified Device Architecture）加速的Instant-NGP （Instant Neural Graphics Primitives）长，但表面重建质量得到明显提升。在真实数据集DTU上，该方法的表面重建误差倒角距离（CD）和新视角合成指标峰值信噪比（PSNR）优于大多数现有方法，较Instant-NGP分别降低了1.21 mm和提高2.93 dB；虽略逊于Neuralangelo （CD提升0.02 mm、PSNR降低2.05 dB），但是训练耗时相较于Neuralangelo缩短了97.5%。可见，该方法能够有效提升训练效率且保证重建精度，实用性好，适用于复杂结构场景的高效三维重建。

关键词: 隐式神经表面, 三维重建, 截断符号距离场, 动态占用网格, 光度一致性约束