MoRel：基于锚框中继双向混合与层次稠密化的长程无闪烁 4D 运动建模
MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectioanl Blending with Hierarchical Densification
把长时序动态场景的形变建模从逐帧高斯搬到关键帧锚框空间，用双向形变加可学习不透明度混合抑制时序闪烁，并用特征方差引导的层次稠密化控制锚框数量——这套「锚框中继 + 双向混合」思路可直接迁移到任何需要长视频、有界显存的动态高斯泼溅或动态 NeRF 管线。
原文依据 we propose a novel 4DGS framework characterized by an Anchor Relay-based Bidirectional Blending (ARBB) mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期 4D 高斯泼溅（4DGS）的进展将 3D 高斯泼溅（3DGS）的高速渲染能力扩展到时间域，使动态场景的实时渲染成为可能。然而，主要遗留挑战之一在于对包含长程运动的动态视频建模：直接扩展已有方法会导致严重的内存爆炸、时序闪烁，以及无法处理随时间出现或消失的遮挡。为应对这些挑战，我们提出一种以锚框中继双向混合（ARBB）机制为特征的新型 4DGS 框架，命名为 MoRel，它能够对长程动态场景进行时序一致且内存高效的建模。本方法在关键帧时间索引处逐步构建局部规范锚框空间，并在锚框层面建模帧间形变，从而增强时序连贯性。通过学习关键帧锚框（KfA）之间的双向形变，并通过可学习的不透明度控制对其进行自适应混合，本方法缓解了时序不连续与闪烁伪影。我们进一步引入特征方差引导的层次稠密化（FHD）方案，依据所分配的特征方差水平对 KfA 进行有效稠密化，同时保持渲染质量。为有效评估模型处理真实世界长程 4D 运动的能力，我们新构建了包含长程 4D 运动的数据集 SelfCap_LR。与以往的动态视频数据集相比，它具有更大的平均动态运动幅度，并在空间上更宽广的范围内采集。总体而言，MoRel 在保持有界内存占用的同时，实现了时序连贯且无闪烁的长程 4D 重建，在基于高斯的动态表示中同时展现出可扩展性与高效性。代码与项目主页将公开发布。
英文原文摘要 1875 字符
Recent advances in 4D Gaussian Splatting (4DGS) have extended the high-speed rendering capability of 3D Gaussian Splatting (3DGS) into the temporal domain, enabling real-time rendering of dynamic scenes.However, one of the major remaining challenges lies in modeling long-range motion-contained dynamic videos, where a naive extension of existing methods leads to severe memory explosion, temporal flickering, and failure to handle appearing or disappearing occlusions over time. To address these challenges, we propose a novel 4DGS framework characterized by an Anchor Relay-based Bidirectional Blending (ARBB) mechanism, named MoRel, which enables temporally consistent and memory-efficient modeling of long-range dynamic scenes.Our method progressively constructs locally canonical anchor spaces at key-frame time index and models inter-frame deformations at the anchor level, enhancing temporal coherence. By learning bidirectional deformations between KfA and adaptively blending them through learnable opacity control, our approach mitigates temporal discontinuities and flickering artifacts.We further introduce a Feature-variance-guided Hierarchical Densification (FHD) scheme that effectively densifies KfA's while keeping rendering quality, based on an assigned level of feature-variance.To effectively evaluate our model's capability to handle real-world long-range 4D motion, we newly compose long-range 4D motion-contained dataset, called SelfCap_ \text LR . It has larger average dynamic motion magnitude, captured at spatially wider spaces, compared to previous dynamic video datasets.Overall, our MoRel achieves temporally coherent and flicker-free long-range 4D reconstruction while maintaining bounded memory usage, demonstrating both scalability and efficiency in dynamic Gaussian-based representations. The code and project page will be publicly released.