A new compression approach for 2D Gaussian-based image representations is aiming at a familiar pain point: once you start storing lots of floating-point parameters per primitive, the bitrate cost ...
The paper proposes Cluster-Guided Vector Quantization (CGVQ), a compression method for 2D Gaussian-based image representations. Instead of quantizing all Gaussian parameters uniformly, it first ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results