22 citations · 60 across the 16 of their papers we have counts for
4 papers · 1 filter
SemanticGen: Video Generation in Semantic Space
Jianhong Bai, Xiaoshi Wu, Xintao Wang +9
State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can gene…
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Minglei Shi, Haolin Wang, Borui Zhang +11
Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generati…
Latent Diffusion Model without Variational Autoencoder
Minglei Shi, Haolin Wang, Wenzhao Zheng +6
Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis…
HPSv3: Towards Wide-Spectrum Human Preference Score
Yuhang Ma, Yunhao Shui, Xiaoshi Wu +2
Evaluating text-to-image generation models requires alignment with human perception, yet existing human-centric metrics are constrained by limited data coverage, suboptimal feature…