上海科技大学知识管理系统

残差辐射场(ReRF)，作为一种高度紧凑的神经表示，以实现长时长动态场景的实时FVV渲染。ReRF显式地对时空特征空间中相邻时间戳之间的残差信息进行建模，使用基于全局坐标的紧凑MLP作为特征解码器。ReRF采用紧凑运动网格以及剩余特征网格来利用帧间特征相似性。还有一种顺序训练方案，以保持运动//残差网格的平滑性和稀疏性。基于ReRF，可以设计实现三个数量级压缩率的特殊FVV编解码器，并且可以实现配套的ReRF播放器以支持动态场景的长持续时间FVV的在线流传输。

Residual Radiance Field (ReRF), as a highly compact neural representation to achieve real-time FVV rendering on long-duration dynamic scenes. ReRF explicitly models the residual information between adjacent timestamps in the spatial-temporal feature space, with a global coordinate-based compact MLP as the feature decoder. ReRF employs a compact motion grid along with a residual feature grid to exploit inter-frame feature similarities. Also a sequential training scheme to maintain the smoothness and the sparsity of the motion//residual grids. Based on ReRF, a special FVV codec may be designed that achieves three orders of magnitudes compression rate and a companion ReRF player may be implemented to support online streaming of long-duration FVVs of dynamic scenes.