文献类型：期刊文献

英文题名：PGgraf: Pose-Guided generative radiance field for novel-views on X-ray

作者：Li, Hangyu[1];Liu, Moquan[1];Wang, Nan[1];Sun, Mengcheng[1];Zhu, Yu[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China

年份：2026

卷号：92

外文期刊名：DISPLAYS

收录：;EI(收录号：20260419953433);WOS:【SCI-EXPANDED(收录号:WOS:001675768500001)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62476088 and 82502467, and the Science and Technology Commission of Shanghai Municipality, China under Grant 20DZ22544000.

语种：英文

外文关键词：X-ray; Neural radiance field; Pose; Novel-view

摘要：In clinical diagnosis, doctors usually judge the information by a few X-rays to avoid excessive ionizing radiation from harming the patient. The recent Neural Radiance Field (NERF) technology contemplates generating novel-views from a single X-ray to assist physicians in diagnosis. In this task, we consider two advantages of X-ray filming over natural images: (1) The medical equipment is fixed, and there is a standardized filming pose. (2) There is an apparent structural prior to X-rays of the same body part at the same pose. Based on such conditions, we propose a Pose-Guided generative radiance field (PGgraf) containing a generator and discriminator. In the training phase, the discriminator combines the image features with two kinds of pose information (ray direction set and camera angle) to guide the generator to synthesize X-rays consistent with the realistic view. In the generator, we design a Density Reconstruction Block (DRB). Unlike the original NERF, which directly estimates the particle density based on the particle positions, the DRB considers all the particle features sampled in a ray and integrally predicts the density of each particle. Experiments comparing qualitative-quantitative on two chest datasets and one knee dataset with state-of-the-art NERF schemes show that PGgraf has a clear advantage in inferring novel-views at different ranges. In the three ranges of 0 degrees to 360 degrees, - -15-15 degrees to 15 degrees, and 75 degrees to 105 degrees, the Peak Signal-to-Noise Ratio (PSNR) improved by an average of 4.18 decibel, and the Learned Perceptual Image Patch Similarity (LPIPS) improved by an average of 50.7%.