RAVQ-HoloNet: Rate-Adaptive Vector-Quantized Hologram Compression
This addresses the high data compression demands limiting holography adoption in AR/VR applications, representing a strong specific gain rather than an incremental improvement.
The paper tackles the problem of hologram compression for AR/VR by introducing a rate-adaptive vector quantization framework, achieving high-fidelity reconstructions with a -33.91% improvement in BD-Rate and 1.02 dB gain in BD-PSNR over state-of-the-art methods at low bit rates.
Holography offers significant potential for AR/VR applications, yet its adoption is limited by the high demands of data compression. Existing deep learning approaches generally lack rate adaptivity within a single network. We present RAVQ-HoloNet, a rate-adaptive vector quantization framework that achieves high-fidelity reconstructions at low and ultra-low bit rates, outperforming current state-of-the-art methods. In low bit, our method exceeds by -33.91% in BD-Rate and achieves a BD-PSNR of 1.02 dB from the best existing method demonstrated by the rate-distortion curve.