Researchers present Cluster-Guided Vector Quantization (CGVQ), a method designed to improve the rate-distortion performance of Gaussian primitive-based image compression. The approach partitions Gaussian parameters into homogeneous groups prior to quantization, addressing the inefficiency caused by storing large numbers of floating-point parameters per primitive.
- CGVQ decreases bits per pixel (bpp) by 20% compared to the baseline method.
- The technique maintains on-par visual quality despite the significant reduction in data size.
- The method leverages clustering to enable higher compression efficiency and accurate parameter reconstruction.
This improvement allows for more efficient storage of high-fidelity image content represented by compact parametric primitives.