Avisek Lahiri

Directed diffusion: Direct control of object placement through attention guidance

Photorealistic Talking Faces from Audio

Text Cutoff Detection for Document Images

Effcient Frameworks for Semantic Inpainting and Learning Under Limited Annotations with Generative Adversarial Networks

Lipsync3d: Data-efficient learning of personalized 3d talking faces from video using pose and lighting normalization

Retinal vessel segmentation under extreme low annotation: A gan based semi-supervised approach

Lightweight Modules for Efficient Deep Learning based Image Restoration

Prior guided gan based semantic inpainting