5 papers
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 (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE object…
Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
Mingxiao Li, Mang Ning, Marie-Francine Moens
Text-to-image generation models have made significant progress in producing high-quality images from textual descriptions, yet they continue to struggle with maintaining subject co…
LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
Haozhe Jia, Wenshuo Chen, Yuqi Lin +8
While current diffusion-based models, typically built on U-Net architectures, have shown promising results on the text-to-motion generation task, they still suffer from semantic mi…
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…
Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
Mang Ning, Albert Ali Salah, Itir Onal Ertugrul
Facial Action Unit (AU) detection has gained significant attention as it enables the breakdown of complex facial expressions into individual muscle movements. In this paper, we rev…