双向自回归扩散用于大复杂运动插值
Bi-directional Autoregressive Diffusion for Large Complex Motion Interpolation
ARVFI 将自回归生成与扩散模型结合，从两端向中间逐帧插值，并利用 DINOv3 高层语义特征作为运动表示，为视频插值中的大复杂运动提供了一种可复用的时序生成框架。
原文依据 ARVFI interpolates in an autoregressive manner from two input frames to the middle ones.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管近期取得了进展，基于扩散的视频帧插值方法在处理大而复杂的运动时仍然表现不佳，导致帧间运动不连续和物体外观不一致。我们观察到这些局限源于当前的全序列插值策略和像素重建训练目标。为解决这些挑战，我们提出了 ARVFI，一种新颖的基于视频扩散的插值方法，用于大复杂运动插值。ARVFI 不是同时生成所有中间帧，而是以自回归方式从两个输入帧向中间帧进行插值。因此，ARVFI 基于所有先前的插值结果来插值距离输入更远的帧，从而产生更平滑的运动过渡和更好的时序一致性。此外，ARVFI 进一步利用 DINOv3 特征作为运动表示，与简单的像素级损失相比，这提供了高层语义以实现准确的运动估计。通过所有这些设计，ARVFI 首先生成中间 DINOv3 特征，然后通过一种有效的帧条件生成方法生成帧。我们的 ARVFI 在插值准确性和视觉质量上始终优于现有方法。
英文原文摘要 1284 字符
Despite recent progress, diffusion-based video frame interpolation methods still struggle with large, complex motions, resulting in discontinuous motions and inconsistent object appearances across frames. We observe that these limitations arise from both the current full-sequence interpolation strategy and the pixel reconstruction training objective. To solve these challenges, we propose ARVFI, a novel video diffusion-based interpolation method for large complex motion interpolation. Instead of generating all intermediate frames simultaneously, ARVFI interpolates in an autoregressive manner from two input frames to the middle ones. Thus, ARVFI interpolates a frame that is further away from the inputs based on all previous interpolation results, resulting in smoother motion transitions and better temporal consistency. Additionally, ARVFI further utilizes DINOv3 features as motion representations, which provide high-level semantics for accurate motion estimation, compared with a simple pixel-level loss. With all these designs, ARVFI generates the intermediate DINOv3 features first and then the frames with an effective conditional generation method for frames. Our ARVFI consistently outperforms existing methods with superior interpolation accuracy and visual quality.