List your company

Image Reconstruction on TextOCR

2.3rFIDMGVQ-G4
2.13243.26374.3955.5263Jul 10, 2025

Evaluation results

MethodLinks
MGVQ-G4Downsample ratio=16, Resolution=512x512, Evaluation Protocol=Zero-shot, Sub-codebooks=42025.072.327.95
SD-VAEDownsample ratio=16, Resolution=512x512, Evaluation Protocol=Zero-shot, Tokenizer Type=Continuous2025.072.3826.3
OpenMagvit2Downsample ratio=16, Resolution=512x512, Evaluation Protocol=Zero-shot2025.074.1923.42
VARDownsample ratio=16, Resolution=512x512, Evaluation Protocol=Zero-shot2025.074.4923.19
LlamaGenDownsample ratio=16, Resolution=512x512, Evaluation Protocol=Zero-shot2025.074.9422.47
VQGANDownsample ratio=16, Resolution=512x512, Evaluation Protocol=Zero-shot2025.076.4921.4