Peyman Milanfar

20

Papers

12

Total Citations

Papers (20)

The Power of Context: How Multimodality Improves Image Super-Resolution

UniRes: Universal Image Restoration for Complex Degradations

CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation

Prompt-tuning Latent Diffusion Models for Inverse Problems

Distortion Agnostic Deep Watermarking

GIFnets: Differentiable GIF Encoding Framework

Rich Features for Perceptual Quality Assessment of UGC Videos

Deblurring via Stochastic Refinement

MAXIM: Multi-Axis MLP for Image Processing

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them From 2D Renderings

VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining

Patch Craft: Video Denoising by Deep Modeling and Patch Matching

COMISR: Compression-Informed Video Super-Resolution

Learning To Resize Images for Computer Vision Tasks

Learning To Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data

MUSIQ: Multi-Scale Image Quality Transformer

SVDiff: Compact Parameter Space for Diffusion Fine-Tuning

Multiscale Structure Guided Diffusion for Image Deblurring

MULLER: Multilayer Laplacian Resizer for Vision

MaxViT: Multi-axis Vision Transformer