MV-Forcing：基于4D锚定的时空自强制方法实现长程多视角视频生成

摘要

近期，视频扩散模型的进展已能通过时域自回归生成长时间单视角视频，或通过双向注意力机制生成短时长多视角合成结果。然而，动态场景下长时长、多视角一致的视频生成问题仍未解决。本文提出MV-Forcing框架，通过引入顺序生成视角间的4D几何桥梁，在单一扩散模型中融合时域与视角维度的自回归。核心洞察在于：自回归3D重建模型能够在自回归生成的视角间自然地建立桥梁。给定完整的源视角后，我们重建其3D结构并渲染下一目标视角的几何先验，再由扩散模型将其精化为高质量视频。为突破教师模型固定时域窗口的限制，我们提出联合去噪机制：在训练阶段将两个视角槽位均初始化为噪声，从而实现时域无界生成。通过结合时空自强迫的分布匹配蒸馏对模型进行精炼，有效弥合了时域与视角序列自回归中的训练-推理暴露偏差。在合成数据与真实数据上的大量实验表明，MV-Forcing能够以单少步学生模型，生成任意时长与任意视角数量、且几何一致的多视角动态场景视频。

English

Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, generating long, multi-view consistent videos of dynamic scenes remains unsolved. In this work, we present MV-Forcing, a framework that composes temporal and view-wise autoregression within a single diffusion model by introducing a 4D geometric bridge between sequentially generated views. Our key insight is that an autoregressive 3D reconstruction model naturally interfaces between autoregressively generated views. Given a completed source view, we reconstruct its 3D structure and render a geometric prior of the next target viewpoint, which the diffusion model refines into a high-quality video. To extend generation beyond the teacher's fixed temporal window, we introduce a joint denoising regime where both view slots are initialized from noise during training, enabling temporally unbounded generation. We distill the model via Distribution Matching Distillation with Spatio-Temporal Self-Forcing, closing the train-inference exposure bias gap for both temporal and view-sequential autoregression. Extensive experiments on both synthetic and real-world data demonstrate that MV-Forcing produces geometrically consistent multi-view videos of dynamic scenes at arbitrary lengths and viewpoint counts using a single few-step student model.