Efficient Image Synthesis with Sphere Latent Encoder
Few-step image generation by decoupling encoding from denoising in a spherical latent space.
I am currently a master’s student in Computer Vision at MBZUAI, under the supervision of Prof. Hao Li. I am also a visiting researcher at Carnegie Mellon University, working with Prof. Fernando De la Torre on cleaning artifacts in 3D Gaussian Splatting. Previously, I worked at Qualcomm AI Research and VinAI.
Before that, I received a B.Eng. in Computer Engineering from the University of Information Technology - VNUHCM.
Few-step image generation by decoupling encoding from denoising in a spherical latent space.
Harmonizing diffusion-based depth estimation and metric depth estimation.
Large reconstruction model with 2D diffusion model.