Mango-GS: 通过多帧节点引导的4D高斯散射提升动态场景重建的空间-时间一致性
Mango-GS: Enhancing Spatio-Temporal Consistency in Dynamic Scenes Reconstruction using Multi-Frame Node-Guided 4D Gaussian Splatting
AI总结：
Mango-GS通过多帧节点引导的4D高斯散射方法，提升动态场景重建的空间-时间一致性，实现高保真重建与实时渲染。
摘要：
重建具有逼真细节和强时间一致性的动态3D场景仍是一个重大挑战。现有的动态场景建模高斯散射方法通常依赖于逐帧优化，这可能导致过度拟合于瞬时状态而不是捕捉底层运动动态。为了解决这个问题，我们提出了Mango-GS，一种多帧、节点引导的高保真4D重建框架。Mango-GS利用一个时间Transformer来建模短帧窗口内的运动依赖性，产生时间一致的变形。为了提高效率，时间建模被限制在稀疏的控制节点集上。每个节点由一个解耦的规范位置和一个潜在代码表示，提供稳定的语义锚点，用于运动传播，并在大运动下防止对应漂移。我们的框架端到端训练，通过输入掩码策略和两个多帧损失增强鲁棒性。广泛的实验表明，Mango-GS实现了最先进的重建质量和实时渲染速度，能够实现动态场景的高保真重建和交互式渲染。
英文摘要：
Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene modeling often rely on per-frame optimization, which can overfit to instantaneous states instead of capturing underlying motion dynamics. To address this, we present Mango-GS, a multi-frame, node-guided framework for high-fidelity 4D reconstruction. Mango-GS leverages a temporal Transformer to model motion dependencies within a short window of frames, producing temporally consistent deformations. For efficiency, temporal modeling is confined to a sparse set of control nodes. Each node is represented by a decoupled canonical position and a latent code, providing a stable semantic anchor for motion propagation and preventing correspondence drift under large motion. Our framework is trained end-to-end, enhanced by an input masking strategy and two multi-frame losses to improve robustness. Extensive experiments demonstrate that Mango-GS achieves state-of-the-art reconstruction quality and real-time rendering speed, enabling high-fidelity reconstruction and interactive rendering of dynamic scenes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
