Hello, I'm Hammond
Working in deep learning, computer vision, inpainting, and diffusion models.
Working in deep learning, computer vision, inpainting, and diffusion models.
Working with U-Net, Vision Transformers, Diffusion Transformers, and Latent Diffusion Models.
Image inpainting with Fourier convolutions, text-guided image editing, and face embedding methods.
Studying how diffusion models generate and edit images, from DDPM to DiT architectures.
Filling in missing or masked parts of images using deep learning approaches.