跟踪引导的 4D 生成：面向 3D 模型动画的基础跟踪器运动先验
Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation
将基础点跟踪器提取的稠密特征级运动先验注入多视图视频扩散模型的中间特征，并用于 4D-GS 的混合运动编码，为动态 4D 生成提供可复用的时序一致性约束手段。
原文依据 explicitly inject tracker-derived motion priors into intermediate feature representations for both multi-view video generation and 4D-GS
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从稀疏输入生成动态 4D 物体十分困难，因为这要求跨视图和时间联合保持外观与运动一致性，同时抑制伪影和时序漂移。我们假设视图差异源于监督信号仅限于像素或潜空间的视频扩散损失，缺乏显式时序感知的特征级跟踪引导。我们提出 Track4DGen，一个两阶段框架，将多视图视频扩散模型与基础点跟踪器及混合 4D 高斯泼溅（4D-GS）重建器耦合。核心思想是将跟踪器导出的运动先验显式注入多视图视频生成和 4D-GS 的中间特征表示中。在第一阶段，我们在扩散生成器内部施加稠密的特征级点对应关系，产生时序一致的特征，从而抑制外观漂移并增强跨视图一致性。在第二阶段，我们使用混合运动编码重建动态 4D-GS，该编码将同位置的扩散特征（携带第一阶段跟踪先验）与六平面特征拼接，并用 4D 球谐函数增强，以实现更高保真的动态建模。Track4DGen 在多视图视频生成和 4D 生成基准上均超越基线，生成时序稳定、文本可编辑的 4D 资产。最后，我们构建了 Sketchfab28，一个用于基准测试以物体为中心的 4D 生成并促进未来研究的高质量数据集。
英文原文摘要 1495 字符
Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artifacts and temporal drift. We hypothesize that the view discrepancy arises from supervision limited to pixel- or latent-space video-diffusion losses, which lack explicitly temporally aware, feature-level tracking guidance.We present Track4DGen, a two-stage framework that couples a multi-view video diffusion model with a foundation point tracker and a hybrid 4D Gaussian Splatting (4D-GS) reconstructor. The central idea is to explicitly inject tracker-derived motion priors into intermediate feature representations for both multi-view video generation and 4D-GS. In Stage One, we enforce dense, feature-level point correspondences inside the diffusion generator, producing temporally consistent features that curb appearance drift and enhance cross-view coherence. In Stage Two, we reconstruct a dynamic 4D-GS using a hybrid motion encoding that concatenates co-located diffusion features (carrying Stage-One tracking priors) with Hex-plane features, and augment them with 4D Spherical Harmonics for higher-fidelity dynamics modeling.Track4DGen surpasses baselines on both multi-view video generation and 4D generation benchmarks, yielding temporally stable, text-editable 4D assets. Lastly, we curate Sketchfab28, a high-quality dataset for benchmarking object-centric 4D generation and fostering future research.