HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Image Reconstruction On Imagenet

评估指标

FID
LPIPS
PSNR
SSIM

评测结果

各个模型在此基准测试上的表现结果

模型名称
FID
LPIPS
PSNR
SSIM
Paper TitleRepository
Taming-VQGAN (16x16)3.640.17719.930.542Taming Transformers for High-Resolution Image Synthesis
Open-Magvit2 (16x16)1.17-21.90-Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
TiTok-S-1281.71---An Image is Worth 32 Tokens for Reconstruction and Generation
VQGAN-LC (16x16)2.620.12023.800.589Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%
OptVQ (16x16x8)0.910.06627.570.729Preventing Local Pitfalls in Vector Quantization via Optimal Transport
MaskBit (16x16)1.66---MaskBit: Embedding-free Image Generation via Bit Tokens
IBQ (16x16)1.000.2030--Taming Scalable Visual Tokenizer for Autoregressive Image Generation-
ViT-VQGAN (16x16)1.28---Vector-quantized Image Modeling with Improved VQGAN
MaskGIT-VQGAN (16x16)2.28---MaskGIT: Masked Generative Image Transformer
RQ-VAE (8x8x16)1.83---Autoregressive Image Generation using Residual Quantization
OptVQ (16x16x4)1.000.07626.590.717Preventing Local Pitfalls in Vector Quantization via Optimal Transport
Mo-VQGAN (16x16x4)1.120.11322.420.673MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
0 of 12 row(s) selected.