用神经辐射场实现多视角一致的伤口分割，提升自动评估精度。
Multi-View Consistent Wound Segmentation With Neural Fields
- 基于NeRF SDF方法，从多视角2D图像重建一致3D伤口结构。
- 在真实数据集上比SOTA视觉变压器模型分割准确率更高。
- 适合医疗影像自动化分析与智能伤口管理研究者使用。
伤口护理常因经济与后勤负担影响全球患者与医院。近年来，计算机视觉与机器学习为医疗专业人员提供支持，尤其伤口分割因可快速自动评估组织状态而备受关注。部分方法已拓展至3D，实现更完整的愈合追踪。但如何从2D图像推断多视角一致的3D结构仍是挑战。本文评估了WoundNeRF——一种基于NeRF SDF的伤口分割方法，利用自动生成的标注进行鲁棒分割。通过与SOTA视觉变压器网络及传统栅格化算法对比，验证了该范式的有效性。代码将公开，以推动该方向发展。
原文摘要 · Abstract (English)
Wound care is often challenged by the economic and logistical burdens that consistently afflict patients and hospitals worldwide. In recent decades, healthcare professionals have sought support from computer vision and machine learning algorithms. In particular, wound segmentation has gained interest due to its ability to provide professionals with fast, automatic tissue assessment from standard RGB images. Some approaches have extended segmentation to 3D, enabling more complete and precise healing progress tracking. However, inferring multi-view consistent 3D structures from 2D images remains a challenge. In this paper, we evaluate WoundNeRF, a NeRF SDF-based method for estimating robust wound segmentations from automatically generated annotations. We demonstrate the potential of this paradigm in recovering accurate segmentations by comparing it against state-of-the-art Vision Transformer networks and conventional rasterisation-based algorithms. The code will be released to facilitate further development in this promising paradigm.
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。