Search Results for author:
Found 3 papers, 0 papers with code
Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning
Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain translation and text-guided image manipulation.
Deep Cross-Modal Steganography Using Neural Representations
The proposed framework employs INRs to represent the secret data, which can handle data of various modalities and resolutions.
I See-Through You: A Framework for Removing Foreground Occlusion in Both Sparse and Dense Light Field Images
To apply LF-DeOcc in both LF datasets, we propose a framework, ISTY, which is defined and divided into three roles: (1) extract LF features, (2) define the occlusion, and (3) inpaint occluded regions.
