CTRL-GS：面向4D Gaussian Splatting的级联时间残差学习
CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
AI总结：
提出CTRL-GS方法，通过分层分解动态场景为“视频-片段-帧”结构并利用残差学习建模时间信号，显著提升了4D Gaussian Splatting在复杂动态场景下的渲染质量与实时性。
摘要：
近期，Gaussian Splatting方法已成为先前Radiance Field方法的理想替代方案，用于对多视角图像或视频捕获的场景进行新视角合成。本文提出了一种针对动态场景的4D Gaussian Splatting新扩展。借鉴残差学习的思想，我们将动态场景分层分解为“视频-片段-帧”结构，其中片段由光流动态调整。随后，受残差学习成功的启发，我们不直接预测时间相关信号，而是将其建模为视频常数值、片段常数值和帧特定残差的总和。该方法使模型更具灵活性，能够适应高度变化的场景。我们在多个已建立的数据集上展示了最先进的视觉质量和实时渲染性能，在包含大运动、遮挡和精细细节的复杂场景中取得了最大改进，而当前方法在这些场景中退化最严重。
英文摘要：
Recently, Gaussian Splatting methods have emerged as a desirable substitute for prior Radiance Field methods for novel-view synthesis of scenes captured with multi-view images or videos. In this work, we propose a novel extension to 4D Gaussian Splatting for dynamic scenes. Drawing on ideas from residual learning, we hierarchically decompose the dynamic scene into a "video-segment-frame" structure, with segments dynamically adjusted by optical flow. Then, instead of directly predicting the time-dependent signals, we model the signal as the sum of video-constant values, segment-constant values, and frame-specific residuals, as inspired by the success of residual learning. This approach allows more flexible models that adapt to highly variable scenes. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets, with the greatest improvements on complex scenes with large movements, occlusions, and fine details, where current methods degrade most.
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。
