Lift4D：為真實場景4D重建協調單視角3D估計

摘要

从单目视频重建动态非刚性物体，需要整合直接观测中的视觉线索与基于数据和先验知识的几何及外观信息。现有方法要么直接从视觉输入学习预测4D表示，要么初始化一个3D表示，随后根据视频证据进行形变与优化。然而，前者受限于4D训练数据的稀缺性，后者仅在初始重建阶段利用先验知识，之后完全依赖视频监督；两者均难以应对包含大幅形变与遮挡的复杂野外场景。我们提出Lift4D，一种测试时优化框架，同时解决上述两类局限。首先，我们通过因果潜在条件化，使现有单视图3D重建模型能生成时间一致的逐帧预测，从而为可变形3D高斯泼溅表示提供连贯的初始化。随后，我们通过遮挡感知优化对该表示进行“雕琢”，在忠实恢复可见表面细节的同时，利用视图条件扩散先验补全未观测区域。实验表明，Lift4D明显优于先前的4D重建方法，尤其是在包含严重遮挡与非刚性运动的挑战性野外序列上。

English

Reconstructing dynamic non-rigid objects from monocular video requires integrating visual cues from direct observations with data-driven priors over geometry and appearance. Prior approaches either learn to directly predict 4D representations from visual input or initialize a 3D representation that is subsequently deformed and refined based on video evidence. However, the former are constrained by the scarcity of 4D training data, while the latter leverage priors only for the initial reconstruction and rely solely on video supervision thereafter; neither handles complex in-the-wild scenarios with large deformations and occlusions well. We present Lift4D, a test-time optimization framework that addresses both limitations. First, we adapt an existing single-view 3D reconstruction model to yield temporally consistent per-frame predictions via causal latent conditioning, providing a coherent initialization for a deformable 3D Gaussian Splatting representation. We then ``sculpt'' this representation to match the input video through an occlusion-aware optimization that faithfully recovers visible surface details while completing unobserved regions using a view-conditioned diffusion prior. We demonstrate that Lift4D clearly improves over prior 4D reconstruction methods, particularly on challenging in-the-wild sequences with severe occlusions and non-rigid motion.