用图像梯度辅助提升复杂表面的法向量估计精度。
Image Gradient-Aided Photometric Stereo Network
- 双分支结构同时处理图像与梯度信息，增强细节感知。
- 在DiLiGenT数据集上平均角度误差达6.46，优于现有方法。
- 适合需要高精度几何重建的复杂纹理场景应用。
光度立体（Photometric stereo, PS）旨在通过不同光照下的影像明暗信息推断表面法向量。近年基于深度学习的PS方法常忽略物体表面复杂性，仅依赖光度图像训练的神经网络在具有局部不连续性的高频区域（如褶皱、显著梯度变化的边缘）易产生模糊结果。为此，本文提出图像梯度辅助光度立体网络（IGA-PSN），采用双分支架构，分别提取光度图像及其梯度特征。此外，引入倒置沙漏回归网络并辅以监督信号，以正则化法向量回归过程。在DiLiGenT基准测试上的实验表明，IGA-PSN在表面法向量估计上超越以往方法，平均角度误差为6.46，同时有效保留了复杂区域的纹理与几何形状。
原文摘要 · Abstract (English)
Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often overlook the complexity of object surfaces. These neural network models, which exclusively rely on photometric images for training, often produce blurred results in high-frequency regions characterized by local discontinuities, such as wrinkles and edges with significant gradient changes. To address this, we propose the Image Gradient-Aided Photometric Stereo Network (IGA-PSN), a dual-branch framework extracting features from both photometric images and their gradients. Furthermore, we incorporate an hourglass regression network along with supervision to regularize normal regression. Experiments on DiLiGenT benchmarks show that IGA-PSN outperforms previous methods in surface normal estimation, achieving a mean angular error of 6.46 while preserving textures and geometric shapes in complex regions.
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。