Micro-Cells Enabling Spatio-Angular Joint Attention for High-Resolution Light Field Editing

Overview of the proposed system. The input includes the pre-editing LF, and one edited SAI. Geometry information is inferred using mono depth estimation to generate a disparity map, for warping-based propagation. The edited LF is refined using a ViT-based composition network to address artifacts like distortion and blurring. LF data is reorganized into micro-cells, converted to MI format, and processed by the composition network to produce the final output.