Diffusion‐based novel view synthesis for <i>X</i> ‐ray imaging

Abstract Background X ‐ray imaging is extensively used in clinical practice due to its low cost, accessibility, and relatively low radiation dose. However, its intrinsic two‐dimensional (2D) projection mechanism inevitably leads to severe structural overlap and lesion occlusion in single‐view acquisitions, substantially limiting the completeness and reliability of anatomical interpretation. Purpose To overcome the loss of spatial information caused by limited viewing angles, this study proposes a diffusion‐based novel view synthesis framework for X ‐ray imaging that directly generates target‐view X ‐ray images from a small number of reference views, without relying on explicit three‐dimensional reconstruction. Methods Built upon the Stable Diffusion framework, the proposed method introduces a lightweight and physically interpretable angular‐difference conditioning mechanism to explicitly model cross‐view geometric relationships. By embedding the relative angular offset between reference and target views into the attention‐based feature interaction process, the model effectively captures view‐dependent structural transformations and synthesizes anatomically consistent novel‐view X ‐ray images. Results Extensive experiments on a synthesized multi‐view X ‐ray dataset demonstrate that the proposed approach achieves robust and stable performance under sparse‐view input conditions, significantly outperforming existing methods in terms of view generalization and structural preservation. In particular, for target view offsets of , , and , the proposed method achieves PSNR values of dB, dB, and dB, respectively, together with consistently improved SSIM and LPIPS scores. Conclusions These results indicate that the proposed framework provides an efficient and flexible solution for supplementing missing X ‐ray views in clinically constrained imaging scenarios.