MoRe：运动感知的前馈 4D 重建 Transformer
MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer
用 attention-forcing 与分组因果注意力把动态运动从静态结构中解耦，为单目视频下的前馈式动态重建提供了可复用的训练策略与注意力设计，可直接迁移到动态 NeRF/3DGS 的快速推理场景。
原文依据 MoRe employs an attention-forcing strategy to disentangle dynamic motion from static structure.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由于运动物体的存在会破坏相机位姿估计，动态 4D 场景的重建仍然具有挑战性。现有的优化方法通过额外监督来缓解这一问题，但大多计算开销高昂，难以用于实时应用。为解决这些局限，我们提出 MoRe，一种前馈式 4D 重建网络，能够从单目视频中高效恢复动态 3D 场景。MoRe 构建于强静态重建骨干之上，采用注意力强制策略将动态运动与静态结构解耦。为进一步提升鲁棒性，我们在涵盖动态与静态场景的大规模多样化数据集上对模型进行微调。此外，我们的分组因果注意力捕获时序依赖，并适应各帧之间变化的词元长度，从而确保时序一致的几何重建。在多个基准上的大量实验表明，MoRe 以极高的效率实现了高质量的动态重建。
英文原文摘要 1047 字符
Reconstructing dynamic 4D scenes remains challenging due to the presence of moving objects that corrupt camera pose estimation. Existing optimization methods alleviate this issue with additional supervision, but they are mostly computationally expensive and impractical in real-time applications. To address these limitations, we propose MoRe, a feedforward 4D reconstruction network that efficiently recovers dynamic 3D scenes from monocular videos. Built upon a strong static reconstruction backbone, MoRe employs an attention-forcing strategy to disentangle dynamic motion from static structure. To further enhance robustness, we fine-tune the model on large-scale, diverse datasets encompassing both dynamic and static scenes. Moreover, our grouped causal attention captures temporal dependencies and adapts to varying token lengths across frames, ensuring temporally coherent geometry reconstruction. Extensive experiments on multiple benchmarks demonstrate that MoRe achieves high-quality dynamic reconstructions with exceptional efficiency.