AI RESEARCH
Generative Video Compression with One-Dimensional Latent Representation
arXiv CS.CV
•
ArXi:2603.15302v1 Announce Type: new Recent advancements in generative video codec (GVC) typically encode video into a 2D latent grid and employ high-capacity generative decoders for reconstruction. However, this paradigm still leaves two key challenges in fully exploiting spatial-temporal redundancy: Spatially, the 2D latent grid inevitably preserves intra-frame redundancy due to its rigid structure, where adjacent patches remain highly similar, thereby necessitating a higher bitrate.