MoCA-Video：面向一致视频编辑的运动感知概念对齐
MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing
AI总结：
MoCA-Video通过在冻结的视频扩散模型潜在空间中进行语义混合，实现无需训练的高质量视频编辑，通过动量修正和伽马残差模块提升时间稳定性和语义一致性。
摘要：
我们提出了MoCA-Video，一种无需训练的视频语义混合框架。该框架在冻结的视频扩散模型的潜在空间中运行，利用不依赖类别的分割与对角线去噪调度器来定位和跟踪目标对象。为确保在语义变化下的时间稳定性，我们引入了基于动量的修正来近似超出训练数据分布的新混合分布，同时引入一个轻量的伽马残差模块以平滑视觉伪影。我们通过SSIM、LPIPS和我们提出的新指标\metricnameabbr来评估模型性能，该指标量化参考与输出之间的语义对齐程度。广泛评估表明，我们的模型在无需重新训练的情况下，始终优于无训练和有训练的基线模型，实现了更优的语义混合和时间一致性。结果表明，对扩散噪声轨迹的结构化操控能够在语义变化下实现可控且高质量的视频编辑。
英文摘要：
Unlike traditional video editing or inpainting, video semantic mixing fuses a reference concept with a moving target entity to produce a hybrid while preserving the source video's motion and layout. We propose MoCA-Video, a training-free framework that steers a frozen video-diffusion denoising trajectory through concept-localized reference injection. At selected low-noise steps, MoCA-Video uses concept attention to localize the target object and injects the reference latent into the localized region, where object structure has formed but appearance remains editable. A momentum-based correction carries the injected prediction across frames to encourage coherent concept integration through the sequence. We further introduce CASS, a CLIP-based metric that measures the output's directional alignment shift toward the reference and away from the source prompt. Using the denoiser's internal attention avoids an external localization model; in our A100 FP16 setup, MoCA-Video takes 3.2 seconds per output frame, excluding preprocessing. Across the evaluated baselines, MoCA-Video achieves the highest CASS, rel-CASS, and ImageReward, while LPIPS-T and FVD expose separate temporal-coherence and video-quality trade-offs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
