EchoVDiff：从任意单帧生成心动周期超声心动图视频
EchoVDiff: Cardiac-Cycle Echocardiography Video Generation from Arbitrary Single Frame
提出相位感知扩散模型，在解耦潜空间中联合建模时序节律与空间语义，实现从任意单帧重建完整心动周期视频；其将生理先验融入扩散范式、解耦潜空间的设计思路可迁移至其他周期性或结构化视频生成任务。
原文依据 We present EchoVDiff, a novel phase-aware diffusion model that reconstructs a full cardiac cycle from any single frame.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单张图像重建生理上合理的心脏视频仍然是生成建模中的一个基本挑战，原因在于超声心动图具有复杂且非线性的周期性动力学。以往的图像到视频（I2V）方法主要关注时序连续性，却往往难以捕捉心脏运动的内在周期性，导致时序连贯性和语义一致性有限。我们提出 EchoVDiff，一种新颖的相位感知扩散模型，能够从任意单帧重建完整的心动周期。EchoVDiff 不直接进行像素合成，而是将生理先验融入扩散范式，学习心脏相位、解剖结构和运动之间的可解释映射。通过在解耦潜空间中联合建模时序节律和空间语义，它实现了可控且生理一致的生成。在 EchoNet-Dynamic 和 EchoNet-Pediatric 上的大量实验表明，EchoVDiff 在保真度和时序连贯性上均持续超越最优方法。值得注意的是，它能够从任意相位准确重建完整心动周期，首次展示了单帧驱动的超声心动图视频生成。
英文原文摘要 1255 字符
Reconstructing a physiologically plausible cardiac video from a single image remains a fundamental challenge in generative modeling, owing to the complex and nonlinear periodic dynamics of echocardiography. Previous image-to-video (I2V) approaches primarily focus on temporal continuity, yet often struggle to capture the intrinsic periodicity of cardiac motion, leading to limited temporal coherence and semantic consistency. We present EchoVDiff, a novel phase-aware diffusion model that reconstructs a full cardiac cycle from any single frame. Instead of direct pixel synthesis, EchoVDiff integrates physiological priors into a diffusion paradigm, learning interpretable mappings between cardiac phase, anatomy, and motion. By jointly modeling temporal rhythm and spatial semantics within a disentangled latent space, it achieves controllable and physiologically consistent generation. Extensive experiments on EchoNet-Dynamic and EchoNet-Pediatric demonstrate that EchoVDiff consistently surpasses state-of-the-art methods in both fidelity and temporal coherence. Remarkably, it enables accurate reconstruction of complete cardiac cycles from arbitrary phases, marking the first demonstration of single-frame-driven echocardiographic video generation.