Tag
RealMe 是一个基于高分辨率视频扩散模型的统一框架，能从稀疏、低分辨率的多视角采集生成 2K 分辨率且 4D 一致的沉浸式体积视频，通过布局感知注意力和频域潜空间监督，在 DNA-Rendering 基准和自建 RealVV 数据集上超越现有方法。
The paper introduces Seed Injection and Temporal Biased Relocation to allocate Gaussian primitives based on predicted spatiotemporal destinations rather than current locations, improving reconstruction of small fast-moving objects and fine textures in dynamic scenes without increasing the Gaussian budget.