clift-light-field-tokens

【数据与研究】Represent 3D scenes as compressed light-field tokens for efficient neural rendering. Multi-view images are tokenized via Plücker coordinates, condensed through K-means clustering, and rendered adaptively. Achieves 5-7× data reduction versus MVSplat while enabling on-the-fly quality-speed tradeoffs: up to 66% FPS improvement with controlled token coun…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准