2 citations · 2 across the 4 of their papers we have counts for
4 papers
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
Mingxi Li
Vector-quantized (VQ) generative models have shown promising results in real-world image super-resolution (Real-ISR). However, existing methods typically rely on a monolithic laten…
Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
Mang Ning, Mingxiao Li, Le Zhang +4
In this paper, we study the diffusability (learnability) of variational autoencoders (VAEs) in latent diffusion. We first derive distribution-free bounds on the maximum achievable…
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
Mang Ning, Mingxiao Li, Jianlin Su +6
This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosin…
Elucidating the Exposure Bias in Diffusion Models
Mang Ning, Mingxiao Li, Jianlin Su +2
Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lack…