We present Motion 3-to-4, a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video and an optional 3D reference mesh. While recent advances have significantly improved 2D, video, and 3D content generation, 4D synthesis remains difficult due to limited training data and the inherent ambiguity of recovering geometry and motion from a monocular viewpoint. Motion 3-to-4 addresses these challenges by decomposing 4D synthesis into static 3D shape generation and motion reconstruction. Using a canonical reference mesh, our model learns a compact motion latent representation and predicts per-frame vertex trajectories to recover complete, temporally coherent geometry. A scalable frame-wise transformer further enables robustness to varying sequence lengths. Evaluations on both standard benchmarks and a new dataset with accurate ground-truth geometry show that Motion 3-to-4 delivers superior fidelity and spatial consistency compared to prior work. Project page is available at https://motion3-to-4.github.io/.

翻译：我们提出Motion 3-to-4，一种前馈框架，用于从单目视频和可选的参考三维网格合成高质量的四维动态物体。尽管近期进展显著提升了二维、视频和三维内容生成的质量，但由于训练数据有限以及从单目视角恢复几何与运动固有的模糊性，四维合成仍然具有挑战性。Motion 3-to-4通过将四维合成分解为静态三维形状生成与运动重建来解决这些难题。利用一个规范参考网格，我们的模型学习一个紧凑的运动潜在表示，并预测逐帧顶点轨迹以恢复完整、时序一致的几何结构。一个可扩展的逐帧Transformer进一步提升了模型对不同序列长度的鲁棒性。在标准基准测试集和包含精确真实几何的新数据集上的评估表明，与现有工作相比，Motion 3-to-4在保真度和空间一致性方面均表现出优越性能。项目页面详见 https://motion3-to-4.github.io/。