TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MGVQ (16x16x4)

MGVQ (16x16x4)

Reported on 8 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical8 results

  • Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
    LPIPS· 2025-07-10
    0.092
    SOTA
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
    PSNR· 2025-07-10
    28.27
    SOTA
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
    SSIM· 2025-07-10
    0.844
    SOTA
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononImageNet
    FID· 2025-07-10
    0.64
    best: 0.49 (MGVQ (16x16x8))
    SOTA
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
    rFID· 2025-07-10
    1.59
    best: 1.07 (SD-VAE (16x16))
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononImageNet
    LPIPS· 2025-07-10
    0.11
    best: 0.066 (OptVQ (16x16x8))
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononImageNet
    PSNR· 2025-07-10
    23.71
    best: 27.57 (OptVQ (16x16x8))
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997
  • Image ReconstructiononImageNet
    SSIM· 2025-07-10
    0.755
    best: 0.787 (MGVQ (16x16x8))
    MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationarXiv:2507.07997